[ { "id": "bedrock/1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0", "slug": "bedrock-1024-x-1024-50-steps-bedrock-amazon-nova-canvas-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.nova-canvas-v1:0", "displayName": "amazon.nova-canvas-v1:0 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": 2600, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", "output_cost_per_image": 0.06 } }, { "id": "bedrock/1024-x-1024/50-steps/stability.stable-diffusion-xl-v1", "slug": "bedrock-1024-x-1024-50-steps-stability-stable-diffusion-xl-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-diffusion-xl-v1", "displayName": "stability.stable-diffusion-xl-v1 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 } }, { "id": "openai/1024-x-1024/dall-e-2", "slug": "openai-1024-x-1024-dall-e-2", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-2", "displayName": "dall-e-2 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.9e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 1.9e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "1024-x-1024/dall-e-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 1.9e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0 } }, { "id": "bedrock/1024-x-1024/max-steps/stability.stable-diffusion-xl-v1", "slug": "bedrock-1024-x-1024-max-steps-stability-stable-diffusion-xl-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-diffusion-xl-v1", "displayName": "stability.stable-diffusion-xl-v1 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 80000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.08 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 } }, { "id": "openai/256-x-256/dall-e-2", "slug": "openai-256-x-256-dall-e-2", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-2", "displayName": "dall-e-2 (256x256)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 2.4414e-7, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 2.4414e-7, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "256-x-256/dall-e-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 2.4414e-7, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0 } }, { "id": "bedrock/512-x-512/50-steps/stability.stable-diffusion-xl-v0", "slug": "bedrock-512-x-512-50-steps-stability-stable-diffusion-xl-v0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-diffusion-xl-v0", "displayName": "stability.stable-diffusion-xl-v0 (512x512)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 18000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.018 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "512-x-512/50-steps/stability.stable-diffusion-xl-v0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.018 } }, { "id": "openai/512-x-512/dall-e-2", "slug": "openai-512-x-512-dall-e-2", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-2", "displayName": "dall-e-2 (512x512)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 6.86e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 6.86e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "512-x-512/dall-e-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 6.86e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0 } }, { "id": "bedrock/512-x-512/max-steps/stability.stable-diffusion-xl-v0", "slug": "bedrock-512-x-512-max-steps-stability-stable-diffusion-xl-v0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-diffusion-xl-v0", "displayName": "stability.stable-diffusion-xl-v0 (512x512)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 36000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.036 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "512-x-512/max-steps/stability.stable-diffusion-xl-v0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.036 } }, { "id": "bedrock/ai21.j2-mid-v1", "slug": "bedrock-ai21-j2-mid-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "ai21.j2-mid-v1", "displayName": "ai21.j2-mid-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 12.5, "outputUsdPer1MTokens": 12.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 12.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000125, "output_cost_per_token": 0.0000125 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ai21.j2-mid-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000125, "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0000125, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/cdk/api/v2/java/software/amazon/awscdk/services/bedrock/FoundationModelIdentifier.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-jurassic2.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-access-product-ids.html" ], "manual_model_modalities_note": "Bedrock exact AI21 Jurassic-2 route id from official docs." } }, { "id": "bedrock/ai21.j2-ultra-v1", "slug": "bedrock-ai21-j2-ultra-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "ai21.j2-ultra-v1", "displayName": "ai21.j2-ultra-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 18.8, "outputUsdPer1MTokens": 18.8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 18.8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000188, "output_cost_per_token": 0.0000188 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ai21.j2-ultra-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000188, "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0000188, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/cdk/api/v2/java/software/amazon/awscdk/services/bedrock/FoundationModelIdentifier.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-access-product-ids.html" ], "manual_model_modalities_note": "Bedrock exact AI21 Jurassic-2 Ultra route id from official docs." } }, { "id": "bedrock/ai21.jamba-1-5-large-v1:0", "slug": "bedrock-ai21-jamba-1-5-large-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "ai21.jamba-1-5-large-v1:0", "displayName": "ai21.jamba-1-5-large-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ai21.jamba-1-5-large-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000008, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact AI21 route id from official docs" } }, { "id": "bedrock/ai21.jamba-1-5-mini-v1:0", "slug": "bedrock-ai21-jamba-1-5-mini-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "ai21.jamba-1-5-mini-v1:0", "displayName": "ai21.jamba-1-5-mini-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ai21.jamba-1-5-mini-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact AI21 route id from official docs" } }, { "id": "bedrock/ai21.jamba-instruct-v1:0", "slug": "bedrock-ai21-jamba-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "ai21.jamba-instruct-v1:0", "displayName": "ai21.jamba-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 7e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 70000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ai21.jamba-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock", "max_input_tokens": 70000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-7, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact AI21 route id from official docs" } }, { "id": "aiml/aiml/dall-e-2", "slug": "aiml-aiml-dall-e-2", "provider": "aiml", "providerSlug": "aiml", "name": "dall-e-2", "displayName": "dall-e-2", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 26000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.026 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/dall-e-2", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.aimlapi.com/" }, "rawLitellm": { "litellm_provider": "aiml", "metadata": { "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" }, "mode": "image_generation", "output_cost_per_image": 0.026, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/dall-e-3", "slug": "aiml-aiml-dall-e-3", "provider": "aiml", "providerSlug": "aiml", "name": "dall-e-3", "displayName": "dall-e-3", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 52000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.052 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/dall-e-3", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.aimlapi.com/" }, "rawLitellm": { "litellm_provider": "aiml", "metadata": { "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" }, "mode": "image_generation", "output_cost_per_image": 0.052, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/flux-pro", "slug": "aiml-aiml-flux-pro", "provider": "aiml", "providerSlug": "aiml", "name": "flux-pro", "displayName": "flux-pro", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 65000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.065 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/flux-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.aimlapi.com/" }, "rawLitellm": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Dev - Development version optimized for experimentation" }, "mode": "image_generation", "output_cost_per_image": 0.065, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/flux-pro/v1.1", "slug": "aiml-aiml-flux-pro-v1-1", "provider": "aiml", "providerSlug": "aiml", "name": "v1.1", "displayName": "v1.1", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 52000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.052 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/flux-pro/v1.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "aiml", "mode": "image_generation", "output_cost_per_image": 0.052, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/flux-pro/v1.1-ultra", "slug": "aiml-aiml-flux-pro-v1-1-ultra", "provider": "aiml", "providerSlug": "aiml", "name": "v1.1-ultra", "displayName": "v1.1-ultra", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 63000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.063 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/flux-pro/v1.1-ultra", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "aiml", "mode": "image_generation", "output_cost_per_image": 0.063, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/flux-realism", "slug": "aiml-aiml-flux-realism", "provider": "aiml", "providerSlug": "aiml", "name": "flux-realism", "displayName": "flux-realism", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 46000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.046 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/flux-realism", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.aimlapi.com/" }, "rawLitellm": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Pro - Professional-grade image generation model" }, "mode": "image_generation", "output_cost_per_image": 0.046, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/flux/dev", "slug": "aiml-aiml-flux-dev", "provider": "aiml", "providerSlug": "aiml", "name": "dev", "displayName": "dev", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 33000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.033 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/flux/dev", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.aimlapi.com/" }, "rawLitellm": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Dev - Development version optimized for experimentation" }, "mode": "image_generation", "output_cost_per_image": 0.033, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/flux/kontext-max/text-to-image", "slug": "aiml-aiml-flux-kontext-max-text-to-image", "provider": "aiml", "providerSlug": "aiml", "name": "text-to-image", "displayName": "text-to-image", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 104000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.104 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/flux/kontext-max/text-to-image", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.aimlapi.com/" }, "rawLitellm": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "mode": "image_generation", "output_cost_per_image": 0.104, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/flux/kontext-pro/text-to-image", "slug": "aiml-aiml-flux-kontext-pro-text-to-image", "provider": "aiml", "providerSlug": "aiml", "name": "text-to-image", "displayName": "text-to-image", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 52000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.052 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/flux/kontext-pro/text-to-image", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.aimlapi.com/" }, "rawLitellm": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "mode": "image_generation", "output_cost_per_image": 0.052, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/flux/schnell", "slug": "aiml-aiml-flux-schnell", "provider": "aiml", "providerSlug": "aiml", "name": "schnell", "displayName": "schnell", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 4000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.004 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/flux/schnell", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.aimlapi.com/" }, "rawLitellm": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Schnell - Fast generation model optimized for speed" }, "mode": "image_generation", "output_cost_per_image": 0.004, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/google/imagen-4.0-ultra-generate-001", "slug": "aiml-aiml-google-imagen-4-0-ultra-generate-001", "provider": "aiml", "providerSlug": "aiml", "name": "imagen-4.0-ultra-generate-001", "displayName": "imagen-4.0-ultra-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 78000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.078 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/google/imagen-4.0-ultra-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.aimlapi.com/api-references/image-models/google/imagen-4-ultra-generate" }, "rawLitellm": { "litellm_provider": "aiml", "metadata": { "notes": "Imagen 4.0 Ultra Generate API - Photorealistic image generation with precise text rendering" }, "mode": "image_generation", "output_cost_per_image": 0.078, "source": "https://docs.aimlapi.com/api-references/image-models/google/imagen-4-ultra-generate", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "aiml/aiml/google/nano-banana-pro", "slug": "aiml-aiml-google-nano-banana-pro", "provider": "aiml", "providerSlug": "aiml", "name": "nano-banana-pro", "displayName": "nano-banana-pro", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 195000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.195 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aiml/google/nano-banana-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview" }, "rawLitellm": { "litellm_provider": "aiml", "metadata": { "notes": "Gemini 3 Pro Image (Nano Banana Pro) - Advanced text-to-image generation with reasoning and 4K resolution support" }, "mode": "image_generation", "output_cost_per_image": 0.195, "source": "https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "bedrock/amazon.nova-canvas-v1:0", "slug": "bedrock-amazon-nova-canvas-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.nova-canvas-v1:0", "displayName": "amazon.nova-canvas-v1:0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": 2600, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "nova_canvas_image_edit": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.nova-canvas-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", "output_cost_per_image": 0.06, "supports_nova_canvas_image_edit": true } }, { "id": "bedrock/us.amazon.nova-canvas-v1:0", "slug": "bedrock-us-amazon-nova-canvas-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.amazon.nova-canvas-v1:0", "displayName": "us.amazon.nova-canvas-v1:0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": 2600, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "nova_canvas_image_edit": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.amazon.nova-canvas-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", "output_cost_per_image": 0.06, "supports_nova_canvas_image_edit": true } }, { "id": "bedrock_converse/us.writer.palmyra-x4-v1:0", "slug": "bedrock_converse-us-writer-palmyra-x4-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.writer.palmyra-x4-v1:0", "displayName": "us.writer.palmyra-x4-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.writer.palmyra-x4-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_pdf_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.html" ], "manual_model_modalities_note": "Bedrock Converse exact Writer route id from official docs" } }, { "id": "bedrock_converse/us.writer.palmyra-x5-v1:0", "slug": "bedrock_converse-us-writer-palmyra-x5-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.writer.palmyra-x5-v1:0", "displayName": "us.writer.palmyra-x5-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.writer.palmyra-x5-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000006, "supports_function_calling": true, "supports_pdf_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Writer route id from official docs" } }, { "id": "bedrock_converse/writer.palmyra-x4-v1:0", "slug": "bedrock_converse-writer-palmyra-x4-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "writer.palmyra-x4-v1:0", "displayName": "writer.palmyra-x4-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "writer.palmyra-x4-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_pdf_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-palmyra-x4.html" ], "manual_model_modalities_note": "Bedrock Converse exact Writer route id from official docs" } }, { "id": "bedrock_converse/writer.palmyra-x5-v1:0", "slug": "bedrock_converse-writer-palmyra-x5-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "writer.palmyra-x5-v1:0", "displayName": "writer.palmyra-x5-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "writer.palmyra-x5-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000006, "supports_function_calling": true, "supports_pdf_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-palmyra-x5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Writer route id from official docs" } }, { "id": "bedrock_converse/amazon.nova-lite-v1:0", "slug": "bedrock_converse-amazon-nova-lite-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "amazon.nova-lite-v1:0", "displayName": "amazon.nova-lite-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.nova-lite-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-7, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-lite.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock_converse/amazon.nova-2-lite-v1:0", "slug": "bedrock_converse-amazon-nova-2-lite-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "amazon.nova-2-lite-v1:0", "displayName": "amazon.nova-2-lite-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "video_input": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.nova-2-lite-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000025, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_video_input": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-lite.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock_converse/amazon.nova-2-pro-preview-20251202-v1:0", "slug": "bedrock_converse-amazon-nova-2-pro-preview-20251202-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "amazon.nova-2-pro-preview-20251202-v1:0", "displayName": "amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.1875, "outputUsdPer1MTokens": 17.5, "cachedInputUsdPer1MTokens": 0.546875, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 2.1875, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.1875, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.46875e-7, "input_cost_per_token": 0.0000021875, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "output_cost_per_token": 0.0000175 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "video_input": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.nova-2-pro-preview-20251202-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.46875e-7, "input_cost_per_token": 0.0000021875, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000175, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_video_input": true, "supports_vision": true } }, { "id": "bedrock_converse/apac.amazon.nova-2-lite-v1:0", "slug": "bedrock_converse-apac-amazon-nova-2-lite-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "apac.amazon.nova-2-lite-v1:0", "displayName": "apac.amazon.nova-2-lite-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.33, "outputUsdPer1MTokens": 2.75, "cachedInputUsdPer1MTokens": 0.0825, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.33, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 8.25e-8, "input_cost_per_token": 3.3e-7, "output_cost_per_token": 0.00000275 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "video_input": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.amazon.nova-2-lite-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 8.25e-8, "input_cost_per_token": 3.3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.00000275, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_video_input": true, "supports_vision": true } }, { "id": "bedrock_converse/apac.amazon.nova-2-pro-preview-20251202-v1:0", "slug": "bedrock_converse-apac-amazon-nova-2-pro-preview-20251202-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "apac.amazon.nova-2-pro-preview-20251202-v1:0", "displayName": "apac.amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.1875, "outputUsdPer1MTokens": 17.5, "cachedInputUsdPer1MTokens": 0.546875, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 2.1875, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.1875, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.46875e-7, "input_cost_per_token": 0.0000021875, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "output_cost_per_token": 0.0000175 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "video_input": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.amazon.nova-2-pro-preview-20251202-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.46875e-7, "input_cost_per_token": 0.0000021875, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000175, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_video_input": true, "supports_vision": true } }, { "id": "bedrock_converse/eu.amazon.nova-2-lite-v1:0", "slug": "bedrock_converse-eu-amazon-nova-2-lite-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.amazon.nova-2-lite-v1:0", "displayName": "eu.amazon.nova-2-lite-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.33, "outputUsdPer1MTokens": 2.75, "cachedInputUsdPer1MTokens": 0.0825, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.33, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 8.25e-8, "input_cost_per_token": 3.3e-7, "output_cost_per_token": 0.00000275 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "video_input": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.amazon.nova-2-lite-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 8.25e-8, "input_cost_per_token": 3.3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.00000275, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_video_input": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-lite.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock_converse/eu.amazon.nova-2-pro-preview-20251202-v1:0", "slug": "bedrock_converse-eu-amazon-nova-2-pro-preview-20251202-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.amazon.nova-2-pro-preview-20251202-v1:0", "displayName": "eu.amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.1875, "outputUsdPer1MTokens": 17.5, "cachedInputUsdPer1MTokens": 0.546875, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 2.1875, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.1875, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.46875e-7, "input_cost_per_token": 0.0000021875, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "output_cost_per_token": 0.0000175 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "video_input": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.amazon.nova-2-pro-preview-20251202-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.46875e-7, "input_cost_per_token": 0.0000021875, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000175, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_video_input": true, "supports_vision": true } }, { "id": "bedrock_converse/us.amazon.nova-2-lite-v1:0", "slug": "bedrock_converse-us-amazon-nova-2-lite-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.amazon.nova-2-lite-v1:0", "displayName": "us.amazon.nova-2-lite-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.33, "outputUsdPer1MTokens": 2.75, "cachedInputUsdPer1MTokens": 0.0825, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.33, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 8.25e-8, "input_cost_per_token": 3.3e-7, "output_cost_per_token": 0.00000275 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "video_input": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.amazon.nova-2-lite-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 8.25e-8, "input_cost_per_token": 3.3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.00000275, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_video_input": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-lite.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock_converse/us.amazon.nova-2-pro-preview-20251202-v1:0", "slug": "bedrock_converse-us-amazon-nova-2-pro-preview-20251202-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.amazon.nova-2-pro-preview-20251202-v1:0", "displayName": "us.amazon.nova-2-pro-preview-20251202-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.1875, "outputUsdPer1MTokens": 17.5, "cachedInputUsdPer1MTokens": 0.546875, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 2.1875, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.1875, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.46875e-7, "input_cost_per_token": 0.0000021875, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "output_cost_per_token": 0.0000175 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "video_input": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.amazon.nova-2-pro-preview-20251202-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.46875e-7, "input_cost_per_token": 0.0000021875, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000175, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_video_input": true, "supports_vision": true } }, { "id": "bedrock/amazon.nova-2-multimodal-embeddings-v1:0", "slug": "bedrock-amazon-nova-2-multimodal-embeddings-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.nova-2-multimodal-embeddings-v1:0", "displayName": "amazon.nova-2-multimodal-embeddings-v1:0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.135, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 60, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.135, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.35e-7, "input_cost_per_image": 0.00006, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8172, "maxInputTokens": 8172, "maxOutputTokens": null, "maxTokens": 8172, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true, "image_input": true, "video_input": true, "audio_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.nova-2-multimodal-embeddings-v1:0", "syncedAt": "2026-05-28", "sourceUrl": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/model-catalog/serverless/amazon.nova-2-multimodal-embeddings-v1:0" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 8172, "max_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.35e-7, "input_cost_per_image": 0.00006, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/model-catalog/serverless/amazon.nova-2-multimodal-embeddings-v1:0", "supports_embedding_image_input": true, "supports_image_input": true, "supports_video_input": true, "supports_audio_input": true } }, { "id": "bedrock_converse/amazon.nova-micro-v1:0", "slug": "bedrock_converse-amazon-nova-micro-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "amazon.nova-micro-v1:0", "displayName": "amazon.nova-micro-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.035, "outputUsdPer1MTokens": 0.14, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.035, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.4e-7 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 128000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.nova-micro-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.5e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-7, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-micro.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock_converse/amazon.nova-pro-v1:0", "slug": "bedrock_converse-amazon-nova-pro-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "amazon.nova-pro-v1:0", "displayName": "amazon.nova-pro-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 3.1999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000032 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.nova-pro-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 0.0000032, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-pro.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock/amazon.rerank-v1:0", "slug": "bedrock-amazon-rerank-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.rerank-v1:0", "displayName": "amazon.rerank-v1:0", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 1, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.001, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 32000, "maxDocumentChunksPerQuery": 100, "maxTokensPerDocumentChunk": 512 }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.rerank-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.001, "input_cost_per_token": 0, "litellm_provider": "bedrock", "max_document_chunks_per_query": 100, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_query_tokens": 32000, "max_tokens": 32000, "max_tokens_per_document_chunk": 512, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "bedrock/amazon.titan-embed-image-v1", "slug": "bedrock-amazon-titan-embed-image-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-embed-image-v1", "displayName": "amazon.titan-embed-image-v1", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 60, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.00006, "input_cost_per_token": 8e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 128, "maxInputTokens": 128, "maxOutputTokens": null, "maxTokens": 128, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true, "image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.titan-embed-image-v1", "syncedAt": "2026-05-28", "sourceUrl": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1" }, "rawLitellm": { "input_cost_per_image": 0.00006, "input_cost_per_token": 8e-7, "litellm_provider": "bedrock", "max_input_tokens": 128, "max_tokens": 128, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024, "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1", "supports_embedding_image_input": true, "supports_image_input": true } }, { "id": "bedrock/amazon.titan-embed-text-v1", "slug": "bedrock-amazon-titan-embed-text-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-embed-text-v1", "displayName": "amazon.titan-embed-text-v1", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1536, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.titan-embed-text-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1536 } }, { "id": "bedrock/amazon.titan-embed-text-v2:0", "slug": "bedrock-amazon-titan-embed-text-v2-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-embed-text-v2:0", "displayName": "amazon.titan-embed-text-v2:0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.titan-embed-text-v2:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024 } }, { "id": "bedrock/amazon.titan-image-generator-v1", "slug": "bedrock-amazon-titan-image-generator-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-image-generator-v1", "displayName": "amazon.titan-image-generator-v1", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 8000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "output_cost_per_image": 0.008, "output_cost_per_image_premium_image": 0.01, "output_cost_per_image_above_512_and_512_pixels": 0.01, "output_cost_per_image_above_512_and_512_pixels_and_premium_image": 0.012 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.titan-image-generator-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "output_cost_per_image": 0.008, "output_cost_per_image_premium_image": 0.01, "output_cost_per_image_above_512_and_512_pixels": 0.01, "output_cost_per_image_above_512_and_512_pixels_and_premium_image": 0.012, "litellm_provider": "bedrock", "mode": "image_generation" } }, { "id": "bedrock/amazon.titan-image-generator-v2", "slug": "bedrock-amazon-titan-image-generator-v2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-image-generator-v2", "displayName": "amazon.titan-image-generator-v2", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 8000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "output_cost_per_image": 0.008, "output_cost_per_image_premium_image": 0.01, "output_cost_per_image_above_1024_and_1024_pixels": 0.01, "output_cost_per_image_above_1024_and_1024_pixels_and_premium_image": 0.012 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.titan-image-generator-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "output_cost_per_image": 0.008, "output_cost_per_image_premium_image": 0.01, "output_cost_per_image_above_1024_and_1024_pixels": 0.01, "output_cost_per_image_above_1024_and_1024_pixels_and_premium_image": 0.012, "litellm_provider": "bedrock", "mode": "image_generation" } }, { "id": "bedrock/amazon.titan-image-generator-v2:0", "slug": "bedrock-amazon-titan-image-generator-v2-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-image-generator-v2:0", "displayName": "amazon.titan-image-generator-v2:0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 8000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "output_cost_per_image": 0.008, "output_cost_per_image_premium_image": 0.01, "output_cost_per_image_above_1024_and_1024_pixels": 0.01, "output_cost_per_image_above_1024_and_1024_pixels_and_premium_image": 0.012 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.titan-image-generator-v2:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "output_cost_per_image": 0.008, "output_cost_per_image_premium_image": 0.01, "output_cost_per_image_above_1024_and_1024_pixels": 0.01, "output_cost_per_image_above_1024_and_1024_pixels_and_premium_image": 0.012, "litellm_provider": "bedrock", "mode": "image_generation" } }, { "id": "bedrock/twelvelabs.marengo-embed-2-7-v1:0", "slug": "bedrock-twelvelabs-marengo-embed-2-7-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "twelvelabs.marengo-embed-2-7-v1:0", "displayName": "twelvelabs.marengo-embed-2-7-v1:0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 70, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 70, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00007, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true, "image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "twelvelabs.marengo-embed-2-7-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00007, "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024, "supports_embedding_image_input": true, "supports_image_input": true } }, { "id": "bedrock/us.twelvelabs.marengo-embed-2-7-v1:0", "slug": "bedrock-us-twelvelabs-marengo-embed-2-7-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.twelvelabs.marengo-embed-2-7-v1:0", "displayName": "us.twelvelabs.marengo-embed-2-7-v1:0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 70, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 100, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 70, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00007, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true, "image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.twelvelabs.marengo-embed-2-7-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00007, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024, "supports_embedding_image_input": true, "supports_image_input": true } }, { "id": "bedrock/eu.twelvelabs.marengo-embed-2-7-v1:0", "slug": "bedrock-eu-twelvelabs-marengo-embed-2-7-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.twelvelabs.marengo-embed-2-7-v1:0", "displayName": "eu.twelvelabs.marengo-embed-2-7-v1:0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 70, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 100, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 70, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00007, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true, "image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.twelvelabs.marengo-embed-2-7-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00007, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024, "supports_embedding_image_input": true, "supports_image_input": true } }, { "id": "bedrock/twelvelabs.pegasus-1-2-v1:0", "slug": "bedrock-twelvelabs-pegasus-1-2-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "twelvelabs.pegasus-1-2-v1:0", "displayName": "twelvelabs.pegasus-1-2-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": 7.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 0.0000075 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "video_input": true } }, "modalities": { "supported": [ "text", "video" ], "input": [ "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "twelvelabs.pegasus-1-2-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 0.0000075, "litellm_provider": "bedrock", "mode": "chat", "supports_video_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-pegasus.html" ], "manual_model_modalities_note": "Bedrock exact TwelveLabs route id from official docs" } }, { "id": "bedrock/us.twelvelabs.pegasus-1-2-v1:0", "slug": "bedrock-us-twelvelabs-pegasus-1-2-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.twelvelabs.pegasus-1-2-v1:0", "displayName": "us.twelvelabs.pegasus-1-2-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": 7.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 0.0000075 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "video_input": true } }, "modalities": { "supported": [ "text", "video" ], "input": [ "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.twelvelabs.pegasus-1-2-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 0.0000075, "litellm_provider": "bedrock", "mode": "chat", "supports_video_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.html" ], "manual_model_modalities_note": "Bedrock exact TwelveLabs geo route id from official docs" } }, { "id": "bedrock/eu.twelvelabs.pegasus-1-2-v1:0", "slug": "bedrock-eu-twelvelabs-pegasus-1-2-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.twelvelabs.pegasus-1-2-v1:0", "displayName": "eu.twelvelabs.pegasus-1-2-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": 7.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 0.0000075 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "video_input": true } }, "modalities": { "supported": [ "text", "video" ], "input": [ "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.twelvelabs.pegasus-1-2-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 0.0000075, "litellm_provider": "bedrock", "mode": "chat", "supports_video_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.html" ], "manual_model_modalities_note": "Bedrock exact TwelveLabs geo route id from official docs" } }, { "id": "bedrock/amazon.titan-text-express-v1", "slug": "bedrock-amazon-titan-text-express-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-text-express-v1", "displayName": "amazon.titan-text-express-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.3, "outputUsdPer1MTokens": 1.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000013, "output_cost_per_token": 0.0000017 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 42000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.titan-text-express-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000013, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.0000017, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Amazon Titan route id from official docs" } }, { "id": "bedrock/amazon.titan-text-lite-v1", "slug": "bedrock-amazon-titan-text-lite-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-text-lite-v1", "displayName": "amazon.titan-text-lite-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 42000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.titan-text-lite-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Amazon Titan route id from official docs" } }, { "id": "bedrock/amazon.titan-text-premier-v1:0", "slug": "bedrock-amazon-titan-text-premier-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-text-premier-v1:0", "displayName": "amazon.titan-text-premier-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 42000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon.titan-text-premier-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0000015, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Amazon Titan route id from official docs" } }, { "id": "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0", "slug": "bedrock-anthropic-claude-3-5-haiku-20241022-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-5-haiku-20241022-v1:0", "displayName": "anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": 0.08, "cacheWriteUsdPer1MTokens": 1, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000001, "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-3-5-haiku-20241022-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000001, "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 8e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000004, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-5-haiku.html", "https://platform.claude.com/docs/en/release-notes/overview", "https://platform.claude.com/docs/en/about-claude/models/overview" ], "manual_model_modalities_note": "Bedrock exact Anthropic route id from official docs" }, "benchmarks": { "aidercodeeditingleaderboard_score_claude35haiku20241022_benchmarkleaderboard_68": { "label": "Aider Code Editing", "category": "coding", "score": 75.2, "scoreText": "75.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Haiku", "exactModelOrSnapshot": "claude-3-5-haiku-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." } } }, { "id": "bedrock_converse/anthropic.claude-haiku-4-5-20251001-v1:0", "slug": "bedrock_converse-anthropic-claude-haiku-4-5-20251001-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": 1.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-haiku-4-5-20251001-v1:0", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock_converse/anthropic.claude-haiku-4-5@20251001", "slug": "bedrock_converse-anthropic-claude-haiku-4-5-20251001", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-haiku-4-5@20251001", "displayName": "anthropic.claude-haiku-4-5@20251001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": 1.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_streaming": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-haiku-4-5@20251001", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_streaming": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic alias from official docs" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0", "slug": "bedrock-anthropic-claude-3-5-sonnet-20240620-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-5-sonnet-20240620-v1:0", "displayName": "anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 30, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.00003, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "cache_creation_input_token_cost_above_1hr": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000015, "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 1000000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-3-5-sonnet-20240620-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.00003, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "cache_creation_input_token_cost_above_1hr": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000015, "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0", "slug": "bedrock-anthropic-claude-3-5-sonnet-20241022-v2-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-5-sonnet-20241022-v2:0", "displayName": "anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 30, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.00003, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "cache_creation_input_token_cost_above_1hr": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-3-5-sonnet-20241022-v2:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.00003, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "cache_creation_input_token_cost_above_1hr": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000015, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/anthropic.claude-3-7-sonnet-20240620-v1:0", "slug": "bedrock-anthropic-claude-3-7-sonnet-20240620-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-7-sonnet-20240620-v1:0", "displayName": "anthropic.claude-3-7-sonnet-20240620-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.5999999999999996, "outputUsdPer1MTokens": 18, "cachedInputUsdPer1MTokens": 0.36, "cacheWriteUsdPer1MTokens": 4.5, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.5999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.0000045, "cache_read_input_token_cost": 3.6e-7, "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-3-7-sonnet-20240620-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.0000045, "cache_read_input_token_cost": 3.6e-7, "input_cost_per_token": 0.0000036, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000018, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock_converse/anthropic.claude-3-7-sonnet-20250219-v1:0", "slug": "bedrock_converse-anthropic-claude-3-7-sonnet-20250219-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-3-7-sonnet-20250219-v1:0", "displayName": "anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-3-7-sonnet-20250219-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-runtime_example_bedrock-runtime_Converse_AnthropicClaudeReasoning_section.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-region-compatibility.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/anthropic.claude-3-haiku-20240307-v1:0", "slug": "bedrock-anthropic-claude-3-haiku-20240307-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-haiku-20240307-v1:0", "displayName": "anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": 0.3125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-3-haiku-20240307-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact Anthropic route id from official docs" } }, { "id": "bedrock/anthropic.claude-3-opus-20240229-v1:0", "slug": "bedrock-anthropic-claude-3-opus-20240229-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-opus-20240229-v1:0", "displayName": "anthropic.claude-3-opus-20240229-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "cache_read_input_token_cost": 0.0000015, "cache_creation_input_token_cost": 0.00001875 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-3-opus-20240229-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000075, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 0.0000015, "cache_creation_input_token_cost": 0.00001875, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact Anthropic route id from official docs" }, "benchmarks": { "aiderrefactoringleaderboard_score_claude3opus20240229_benchmarkleaderboard_69": { "label": "Aider Refactoring", "category": "coding", "score": 72.3, "scoreText": "72.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/refactor.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3 Opus", "exactModelOrSnapshot": "claude-3-opus-20240229", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Refactoring leaderboard row; diff edit format." } } }, { "id": "bedrock/anthropic.claude-3-sonnet-20240229-v1:0", "slug": "bedrock-anthropic-claude-3-sonnet-20240229-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-sonnet-20240229-v1:0", "displayName": "anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-3-sonnet-20240229-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-claude.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic route id from official docs." } }, { "id": "bedrock/anthropic.claude-instant-v1", "slug": "bedrock-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0000024, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el", "https://docs.aws.amazon.com/cdk/api/v2/java/software/amazon/awscdk/services/bedrock/FoundationModelIdentifier.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic route id from official docs." } }, { "id": "bedrock_converse/anthropic.claude-opus-4-1-20250805-v1:0", "slug": "bedrock_converse-anthropic-claude-opus-4-1-20250805-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-opus-4-1-20250805-v1:0", "displayName": "anthropic.claude-opus-4-1-20250805-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-opus-4-1-20250805-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-1.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "bedrock_converse/anthropic.claude-opus-4-20250514-v1:0", "slug": "bedrock_converse-anthropic-claude-opus-4-20250514-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-opus-4-20250514-v1:0", "displayName": "anthropic.claude-opus-4-20250514-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-opus-4-20250514-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "bedrock_converse/anthropic.claude-opus-4-5-20251101-v1:0", "slug": "bedrock_converse-anthropic-claude-opus-4-5-20251101-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "minimal_reasoning_effort": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-opus-4-5-20251101-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "bedrock_converse/anthropic.claude-opus-4-6-v1", "slug": "bedrock_converse-anthropic-claude-opus-4-6-v1", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-opus-4-6-v1", "displayName": "anthropic.claude-opus-4-6-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-opus-4-6-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "bedrock_converse/global.anthropic.claude-opus-4-6-v1", "slug": "bedrock_converse-global-anthropic-claude-opus-4-6-v1", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "global.anthropic.claude-opus-4-6-v1", "displayName": "global.anthropic.claude-opus-4-6-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "global.anthropic.claude-opus-4-6-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "bedrock_converse/us.anthropic.claude-opus-4-6-v1", "slug": "bedrock_converse-us-anthropic-claude-opus-4-6-v1", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.anthropic.claude-opus-4-6-v1", "displayName": "us.anthropic.claude-opus-4-6-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 27.5, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": 6.875, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000006875, "cache_creation_input_token_cost_above_1hr": 0.000011, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-opus-4-6-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000006875, "cache_creation_input_token_cost_above_1hr": 0.000011, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "bedrock_converse/eu.anthropic.claude-opus-4-6-v1", "slug": "bedrock_converse-eu-anthropic-claude-opus-4-6-v1", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.anthropic.claude-opus-4-6-v1", "displayName": "eu.anthropic.claude-opus-4-6-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 27.5, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": 6.875, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000006875, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-opus-4-6-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000006875, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "bedrock_converse/au.anthropic.claude-opus-4-6-v1", "slug": "bedrock_converse-au-anthropic-claude-opus-4-6-v1", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "au.anthropic.claude-opus-4-6-v1", "displayName": "au.anthropic.claude-opus-4-6-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 27.5, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": 6.875, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000006875, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "au.anthropic.claude-opus-4-6-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000006875, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "bedrock_converse/anthropic.claude-opus-4-7", "slug": "bedrock_converse-anthropic-claude-opus-4-7", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-opus-4-7", "displayName": "anthropic.claude-opus-4-7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": true }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true, "native_structured_output": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-opus-4-7", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-7.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "bedrock/anthropic.claude-mythos-preview", "slug": "bedrock-anthropic-claude-mythos-preview", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-mythos-preview", "displayName": "anthropic.claude-mythos-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true, "prompt_caching": false, "reasoning": true, "minimal_reasoning_effort": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-mythos-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_minimal_reasoning_effort": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/id_id/bedrock/latest/userguide/model-card-anthropic-claude-mythos-preview.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic route id from official docs" } }, { "id": "bedrock_converse/global.anthropic.claude-opus-4-7", "slug": "bedrock_converse-global-anthropic-claude-opus-4-7", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "global.anthropic.claude-opus-4-7", "displayName": "global.anthropic.claude-opus-4-7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": true }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true, "native_structured_output": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "global.anthropic.claude-opus-4-7", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-7.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "bedrock_converse/us.anthropic.claude-opus-4-7", "slug": "bedrock_converse-us-anthropic-claude-opus-4-7", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.anthropic.claude-opus-4-7", "displayName": "us.anthropic.claude-opus-4-7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 27.5, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": 6.875, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000006875, "cache_creation_input_token_cost_above_1hr": 0.000011, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": true }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true, "native_structured_output": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-opus-4-7", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000006875, "cache_creation_input_token_cost_above_1hr": 0.000011, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-7.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "bedrock_converse/eu.anthropic.claude-opus-4-7", "slug": "bedrock_converse-eu-anthropic-claude-opus-4-7", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.anthropic.claude-opus-4-7", "displayName": "eu.anthropic.claude-opus-4-7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 27.5, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": 6.875, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000006875, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": true }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true, "native_structured_output": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-opus-4-7", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000006875, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-7.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "bedrock_converse/au.anthropic.claude-opus-4-7", "slug": "bedrock_converse-au-anthropic-claude-opus-4-7", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "au.anthropic.claude-opus-4-7", "displayName": "au.anthropic.claude-opus-4-7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 27.5, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": 6.875, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000006875, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": true }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true, "native_structured_output": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "au.anthropic.claude-opus-4-7", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000006875, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-7.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "bedrock_converse/anthropic.claude-sonnet-4-6", "slug": "bedrock_converse-anthropic-claude-sonnet-4-6", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-sonnet-4-6", "displayName": "anthropic.claude-sonnet-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-sonnet-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock_converse/global.anthropic.claude-sonnet-4-6", "slug": "bedrock_converse-global-anthropic-claude-sonnet-4-6", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "global.anthropic.claude-sonnet-4-6", "displayName": "global.anthropic.claude-sonnet-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "global.anthropic.claude-sonnet-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock_converse/us.anthropic.claude-sonnet-4-6", "slug": "bedrock_converse-us-anthropic-claude-sonnet-4-6", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.anthropic.claude-sonnet-4-6", "displayName": "us.anthropic.claude-sonnet-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_creation_input_token_cost_above_1hr": 0.0000066, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-sonnet-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_creation_input_token_cost_above_1hr": 0.0000066, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock_converse/eu.anthropic.claude-sonnet-4-6", "slug": "bedrock_converse-eu-anthropic-claude-sonnet-4-6", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.anthropic.claude-sonnet-4-6", "displayName": "eu.anthropic.claude-sonnet-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-sonnet-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock_converse/au.anthropic.claude-sonnet-4-6", "slug": "bedrock_converse-au-anthropic-claude-sonnet-4-6", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "au.anthropic.claude-sonnet-4-6", "displayName": "au.anthropic.claude-sonnet-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "au.anthropic.claude-sonnet-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock_converse/jp.anthropic.claude-sonnet-4-6", "slug": "bedrock_converse-jp-anthropic-claude-sonnet-4-6", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "jp.anthropic.claude-sonnet-4-6", "displayName": "jp.anthropic.claude-sonnet-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "native_structured_output": true, "output_config": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jp.anthropic.claude-sonnet-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_output_config": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-6.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock_converse/anthropic.claude-sonnet-4-20250514-v1:0", "slug": "bedrock_converse-anthropic-claude-sonnet-4-20250514-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-sonnet-4-20250514-v1:0", "displayName": "anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-sonnet-4-20250514-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "bedrock_converse/anthropic.claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock_converse-anthropic-claude-sonnet-4-5-20250929-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/anthropic.claude-v1", "slug": "bedrock-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024 } }, { "id": "bedrock/anthropic.claude-v2:1", "slug": "bedrock-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude 2.1 route id from official docs." } }, { "id": "anyscale/anyscale/HuggingFaceH4/zephyr-7b-beta", "slug": "anyscale-anyscale-huggingfaceh4-zephyr-7b-beta", "provider": "anyscale", "providerSlug": "anyscale", "name": "zephyr-7b-beta", "displayName": "zephyr-7b-beta", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/HuggingFaceH4/zephyr-7b-beta", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-7 } }, { "id": "anyscale/anyscale/codellama/CodeLlama-34b-Instruct-hf", "slug": "anyscale-anyscale-codellama-codellama-34b-instruct-hf", "provider": "anyscale", "providerSlug": "anyscale", "name": "CodeLlama-34b-Instruct-hf", "displayName": "CodeLlama-34b-Instruct-hf", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/codellama/CodeLlama-34b-Instruct-hf", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000001 }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "anyscale/anyscale/codellama/CodeLlama-70b-Instruct-hf", "slug": "anyscale-anyscale-codellama-codellama-70b-instruct-hf", "provider": "anyscale", "providerSlug": "anyscale", "name": "CodeLlama-70b-Instruct-hf", "displayName": "CodeLlama-70b-Instruct-hf", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/codellama/CodeLlama-70b-Instruct-hf", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000001, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "anyscale/anyscale/google/gemma-7b-it", "slug": "anyscale-anyscale-google-gemma-7b-it", "provider": "anyscale", "providerSlug": "anyscale", "name": "gemma-7b-it", "displayName": "gemma-7b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/google/gemma-7b-it", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-7, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" } }, { "id": "anyscale/anyscale/meta-llama/Llama-2-13b-chat-hf", "slug": "anyscale-anyscale-meta-llama-llama-2-13b-chat-hf", "provider": "anyscale", "providerSlug": "anyscale", "name": "Llama-2-13b-chat-hf", "displayName": "Llama-2-13b-chat-hf", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/meta-llama/Llama-2-13b-chat-hf", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-7 } }, { "id": "anyscale/anyscale/meta-llama/Llama-2-70b-chat-hf", "slug": "anyscale-anyscale-meta-llama-llama-2-70b-chat-hf", "provider": "anyscale", "providerSlug": "anyscale", "name": "Llama-2-70b-chat-hf", "displayName": "Llama-2-70b-chat-hf", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/meta-llama/Llama-2-70b-chat-hf", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000001 } }, { "id": "anyscale/anyscale/meta-llama/Llama-2-7b-chat-hf", "slug": "anyscale-anyscale-meta-llama-llama-2-7b-chat-hf", "provider": "anyscale", "providerSlug": "anyscale", "name": "Llama-2-7b-chat-hf", "displayName": "Llama-2-7b-chat-hf", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/meta-llama/Llama-2-7b-chat-hf", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-7 } }, { "id": "anyscale/anyscale/meta-llama/Meta-Llama-3-70B-Instruct", "slug": "anyscale-anyscale-meta-llama-meta-llama-3-70b-instruct", "provider": "anyscale", "providerSlug": "anyscale", "name": "Meta-Llama-3-70B-Instruct", "displayName": "Meta-Llama-3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/meta-llama/Meta-Llama-3-70B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000001, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" } }, { "id": "anyscale/anyscale/meta-llama/Meta-Llama-3-8B-Instruct", "slug": "anyscale-anyscale-meta-llama-meta-llama-3-8b-instruct", "provider": "anyscale", "providerSlug": "anyscale", "name": "Meta-Llama-3-8B-Instruct", "displayName": "Meta-Llama-3-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/meta-llama/Meta-Llama-3-8B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-7, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" } }, { "id": "anyscale/anyscale/mistralai/Mistral-7B-Instruct-v0.1", "slug": "anyscale-anyscale-mistralai-mistral-7b-instruct-v0-1", "provider": "anyscale", "providerSlug": "anyscale", "name": "Mistral-7B-Instruct-v0.1", "displayName": "Mistral-7B-Instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/mistralai/Mistral-7B-Instruct-v0.1", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-7, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", "supports_function_calling": true }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "anyscale/anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1", "slug": "anyscale-anyscale-mistralai-mixtral-8x22b-instruct-v0-1", "provider": "anyscale", "providerSlug": "anyscale", "name": "Mixtral-8x22B-Instruct-v0.1", "displayName": "Mixtral-8x22B-Instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "anyscale", "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9e-7, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", "supports_function_calling": true }, "benchmarks": { "gsm8kmaj8_8shot_mixtral8x22binstruct_officiallaunchpost_212": { "label": "GSM8K maj@8", "category": "math", "score": 90.8, "scoreText": "90.8%", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on GSM8K maj@8." }, "mathmaj4_4shot_mixtral8x22binstruct_officiallaunchpost_213": { "label": "Math maj@4", "category": "math", "score": 44.6, "scoreText": "44.6%", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on Math maj@4." } } }, { "id": "anyscale/anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1", "slug": "anyscale-anyscale-mistralai-mixtral-8x7b-instruct-v0-1", "provider": "anyscale", "providerSlug": "anyscale", "name": "Mixtral-8x7B-Instruct-v0.1", "displayName": "Mixtral-8x7B-Instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-7, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", "supports_function_calling": true } }, { "id": "bedrock_converse/apac.amazon.nova-lite-v1:0", "slug": "bedrock_converse-apac-amazon-nova-lite-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "apac.amazon.nova-lite-v1:0", "displayName": "apac.amazon.nova-lite-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.063, "outputUsdPer1MTokens": 0.252, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.063, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.3e-8, "output_cost_per_token": 2.52e-7 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.amazon.nova-lite-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6.3e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.52e-7, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-lite.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon inference-profile route id from official docs" } }, { "id": "bedrock_converse/apac.amazon.nova-micro-v1:0", "slug": "bedrock_converse-apac-amazon-nova-micro-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "apac.amazon.nova-micro-v1:0", "displayName": "apac.amazon.nova-micro-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.037, "outputUsdPer1MTokens": 0.148, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.037, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.7e-8, "output_cost_per_token": 1.48e-7 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 128000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.amazon.nova-micro-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.7e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.48e-7, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-micro.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon inference-profile route id from official docs" } }, { "id": "bedrock_converse/apac.amazon.nova-pro-v1:0", "slug": "bedrock_converse-apac-amazon-nova-pro-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "apac.amazon.nova-pro-v1:0", "displayName": "apac.amazon.nova-pro-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.84, "outputUsdPer1MTokens": 3.36, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.84, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8.4e-7, "output_cost_per_token": 0.00000336 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.amazon.nova-pro-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8.4e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 0.00000336, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-pro.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon inference-profile route id from official docs" } }, { "id": "bedrock/apac.anthropic.claude-3-5-sonnet-20240620-v1:0", "slug": "bedrock-apac-anthropic-claude-3-5-sonnet-20240620-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0", "displayName": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact APAC Anthropic route id from official docs." }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/apac.anthropic.claude-3-5-sonnet-20241022-v2:0", "slug": "bedrock-apac-anthropic-claude-3-5-sonnet-20241022-v2-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0", "displayName": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact APAC Anthropic route id from official docs." }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/apac.anthropic.claude-3-haiku-20240307-v1:0", "slug": "bedrock-apac-anthropic-claude-3-haiku-20240307-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "apac.anthropic.claude-3-haiku-20240307-v1:0", "displayName": "apac.anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": 0.3125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.anthropic.claude-3-haiku-20240307-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.html" ], "manual_model_modalities_note": "Bedrock exact APAC Anthropic route id from official docs." } }, { "id": "bedrock_converse/apac.anthropic.claude-haiku-4-5-20251001-v1:0", "slug": "bedrock_converse-apac-anthropic-claude-haiku-4-5-20251001-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "apac.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "apac.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 5.5, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": 1.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000001375, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000055 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.anthropic.claude-haiku-4-5-20251001-v1:0", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000001375, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000055, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock/apac.anthropic.claude-3-sonnet-20240229-v1:0", "slug": "bedrock-apac-anthropic-claude-3-sonnet-20240229-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "apac.anthropic.claude-3-sonnet-20240229-v1:0", "displayName": "apac.anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.anthropic.claude-3-sonnet-20240229-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact APAC Anthropic route id from official docs." } }, { "id": "bedrock_converse/apac.anthropic.claude-sonnet-4-20250514-v1:0", "slug": "bedrock_converse-apac-anthropic-claude-sonnet-4-20250514-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "apac.anthropic.claude-sonnet-4-20250514-v1:0", "displayName": "apac.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "apac.anthropic.claude-sonnet-4-20250514-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "assemblyai/assemblyai/best", "slug": "assemblyai-assemblyai-best", "provider": "assemblyai", "providerSlug": "assemblyai", "name": "best", "displayName": "best", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00003333, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00003333, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "assemblyai/best", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.00003333, "litellm_provider": "assemblyai", "mode": "audio_transcription", "output_cost_per_second": 0, "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "assemblyai/assemblyai/nano", "slug": "assemblyai-assemblyai-nano", "provider": "assemblyai", "providerSlug": "assemblyai", "name": "nano", "displayName": "nano", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00010278, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00010278, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "assemblyai/nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.00010278, "litellm_provider": "assemblyai", "mode": "audio_transcription", "output_cost_per_second": 0, "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "bedrock_converse/au.anthropic.claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock_converse-au-anthropic-claude-sonnet-4-5-20250929-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6.6000000000000005, "above200kOutputUsdPer1MTokens": 24.75, "above200kCachedInputUsdPer1MTokens": 0.66, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "azure/azure/ada", "slug": "azure-azure-ada", "provider": "Azure", "providerSlug": "azure", "name": "ada", "displayName": "ada", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/ada", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "azure", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "azure/azure/codex-mini", "slug": "azure-azure-codex-mini", "provider": "Azure", "providerSlug": "azure", "name": "codex-mini", "displayName": "codex-mini", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": 0.375, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3.75e-7, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/codex-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 3.75e-7, "input_cost_per_token": 0.0000015, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.000006, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure/azure/command-r-plus", "slug": "azure-azure-command-r-plus", "provider": "Azure", "providerSlug": "azure", "name": "command-r-plus", "displayName": "command-r-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/command-r-plus", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners" ], "manual_model_modalities_note": "Azure exact partner model id from official docs." } }, { "id": "azure_ai/azure_ai/claude-haiku-4-5", "slug": "azure_ai-azure_ai-claude-haiku-4-5", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "claude-haiku-4-5", "displayName": "claude-haiku-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": 1.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/claude-haiku-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000005, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/ru-ru/azure/foundry/foundry-models/how-to/use-foundry-models-claude" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "azure_ai/azure_ai/claude-opus-4-5", "slug": "azure_ai-azure_ai-claude-opus-4-5", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "claude-opus-4-5", "displayName": "claude-opus-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "minimal_reasoning_effort": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/claude-opus-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/ru-ru/azure/foundry/foundry-models/how-to/use-foundry-models-claude" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "azure_ai/azure_ai/claude-opus-4-6", "slug": "azure_ai-azure_ai-claude-opus-4-6", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "claude-opus-4-6", "displayName": "claude-opus-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "output_config": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/claude-opus-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/ru-ru/azure/foundry/foundry-models/how-to/use-foundry-models-claude" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "azure_ai/azure_ai/claude-opus-4-7", "slug": "azure_ai-azure_ai-claude-opus-4-7", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "claude-opus-4-7", "displayName": "claude-opus-4-7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": true }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/claude-opus-4-7", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 159, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/ru-ru/azure/foundry/foundry-models/how-to/use-foundry-models-claude" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "azure_ai/azure_ai/claude-opus-4-1", "slug": "azure_ai-azure_ai-claude-opus-4-1", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "claude-opus-4-1", "displayName": "claude-opus-4-1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.00003, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/claude-opus-4-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.00003, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/ru-ru/azure/foundry/foundry-models/how-to/use-foundry-models-claude" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "azure_ai/azure_ai/claude-sonnet-4-5", "slug": "azure_ai-azure_ai-claude-sonnet-4-5", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "claude-sonnet-4-5", "displayName": "claude-sonnet-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/claude-sonnet-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/ru-ru/azure/foundry/foundry-models/how-to/use-foundry-models-claude" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "azure_ai/azure_ai/claude-sonnet-4-6", "slug": "azure_ai-azure_ai-claude-sonnet-4-6", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "claude-sonnet-4-6", "displayName": "claude-sonnet-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "output_config": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/claude-sonnet-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_output_config": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-claude?view=foundry-classic" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "azure/azure/computer-use-preview", "slug": "azure-azure-computer-use-preview", "provider": "Azure", "providerSlug": "azure", "name": "computer-use-preview", "displayName": "computer-use-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000012 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 8192, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/computer-use-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 0.000012, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "azure/azure/container", "slug": "azure-azure-container", "provider": "Azure", "providerSlug": "azure", "name": "container", "displayName": "container", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": 0.03, "rawPricing": { "code_interpreter_cost_per_session": 0.03 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/container", "syncedAt": "2026-05-28" }, "rawLitellm": { "code_interpreter_cost_per_session": 0.03, "litellm_provider": "azure", "mode": "chat" } }, { "id": "azure_ai/azure_ai/gpt-oss-120b", "slug": "azure_ai-azure_ai-gpt-oss-120b", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/gpt-oss-120b", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "azure_ai/azure_ai/gpt-5.4", "slug": "azure_ai-azure_ai-gpt-5-4", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "gpt-5.4", "displayName": "gpt-5.4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 5, "priorityOutputUsdPer1MTokens": 30, "priorityCachedInputUsdPer1MTokens": 0.5, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 5, "above272kOutputUsdPer1MTokens": 22.5, "above272kCachedInputUsdPer1MTokens": 0.5, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/gpt-5.4", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.azure.com/catalog/models/gpt-5.4" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "litellm_provider": "azure_ai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "source": "https://ai.azure.com/catalog/models/gpt-5.4", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/gpt-5.4" ], "manual_model_modalities_note": "Azure AI exact route id from official catalog." }, "benchmarks": { "livebench_livebenchscore_gpt54thinkingxhigheffort_benchmarkleaderboard_228": { "label": "LiveBench", "category": "general_knowledge", "score": 80.28, "scoreText": "80.28", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "GPT-5.4 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt54high_benchmarkleaderboard_244": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1483, "scoreText": "1483±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "gpt-5.4-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." } } }, { "id": "azure_ai/azure_ai/gpt-5.4-2026-03-05", "slug": "azure_ai-azure_ai-gpt-5-4-2026-03-05", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "gpt-5.4-2026-03-05", "displayName": "gpt-5.4-2026-03-05", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 5, "priorityOutputUsdPer1MTokens": 30, "priorityCachedInputUsdPer1MTokens": 0.5, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 5, "above272kOutputUsdPer1MTokens": 22.5, "above272kCachedInputUsdPer1MTokens": 0.5, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/gpt-5.4-2026-03-05", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.azure.com/catalog/models/gpt-5.4" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "litellm_provider": "azure_ai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "source": "https://ai.azure.com/catalog/models/gpt-5.4", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/gpt-5.4" ], "manual_model_modalities_note": "Azure AI exact versioned route id from official catalog." }, "benchmarks": { "livebench_livebenchscore_gpt54thinkingxhigheffort_benchmarkleaderboard_228": { "label": "LiveBench", "category": "general_knowledge", "score": 80.28, "scoreText": "80.28", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "GPT-5.4 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt54high_benchmarkleaderboard_244": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1483, "scoreText": "1483±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "gpt-5.4-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." } } }, { "id": "azure_ai/azure_ai/gpt-5.4-pro", "slug": "azure_ai-azure_ai-gpt-5-4-pro", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "gpt-5.4-pro", "displayName": "gpt-5.4-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 180, "cachedInputUsdPer1MTokens": 3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 60, "priorityOutputUsdPer1MTokens": 360, "priorityCachedInputUsdPer1MTokens": 6, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 60, "above272kOutputUsdPer1MTokens": 270, "above272kCachedInputUsdPer1MTokens": 6, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/gpt-5.4-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.azure.com/catalog/models/gpt-5.4-pro" }, "rawLitellm": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054, "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/gpt-5.4-pro-2026-03-05", "slug": "azure_ai-azure_ai-gpt-5-4-pro-2026-03-05", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "gpt-5.4-pro-2026-03-05", "displayName": "gpt-5.4-pro-2026-03-05", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 180, "cachedInputUsdPer1MTokens": 3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 60, "priorityOutputUsdPer1MTokens": 360, "priorityCachedInputUsdPer1MTokens": 6, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 60, "above272kOutputUsdPer1MTokens": 270, "above272kCachedInputUsdPer1MTokens": 6, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/gpt-5.4-pro-2026-03-05", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.azure.com/catalog/models/gpt-5.4-pro" }, "rawLitellm": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054, "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/gpt-5.4-mini", "slug": "azure_ai-azure_ai-gpt-5-4-mini", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "gpt-5.4-mini", "displayName": "gpt-5.4-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.75, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 1.5, "priorityOutputUsdPer1MTokens": 9, "priorityCachedInputUsdPer1MTokens": 0.15, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 1.5, "above272kOutputUsdPer1MTokens": 6.75, "above272kCachedInputUsdPer1MTokens": 0.15, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_above_272k_tokens": 1.5e-7, "cache_read_input_token_cost_priority": 1.5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 3e-7, "input_cost_per_token": 7.5e-7, "input_cost_per_token_above_272k_tokens": 0.0000015, "input_cost_per_token_priority": 0.0000015, "input_cost_per_token_above_272k_tokens_priority": 0.000003, "output_cost_per_token": 0.0000045, "output_cost_per_token_above_272k_tokens": 0.00000675, "output_cost_per_token_priority": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.0000135 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 400000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/gpt-5.4-mini", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.azure.com/catalog/models/gpt-5.4-mini" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_above_272k_tokens": 1.5e-7, "cache_read_input_token_cost_priority": 1.5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 3e-7, "input_cost_per_token": 7.5e-7, "input_cost_per_token_above_272k_tokens": 0.0000015, "input_cost_per_token_priority": 0.0000015, "input_cost_per_token_above_272k_tokens_priority": 0.000003, "litellm_provider": "azure_ai", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000045, "output_cost_per_token_above_272k_tokens": 0.00000675, "output_cost_per_token_priority": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.0000135, "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/gpt-5.4-mini" ], "manual_model_modalities_note": "Azure AI exact route id from official catalog." } }, { "id": "azure_ai/azure_ai/gpt-5.4-mini-2026-03-17", "slug": "azure_ai-azure_ai-gpt-5-4-mini-2026-03-17", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "gpt-5.4-mini-2026-03-17", "displayName": "gpt-5.4-mini-2026-03-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.75, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 1.5, "priorityOutputUsdPer1MTokens": 9, "priorityCachedInputUsdPer1MTokens": 0.15, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 1.5, "above272kOutputUsdPer1MTokens": 6.75, "above272kCachedInputUsdPer1MTokens": 0.15, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_above_272k_tokens": 1.5e-7, "cache_read_input_token_cost_priority": 1.5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 3e-7, "input_cost_per_token": 7.5e-7, "input_cost_per_token_above_272k_tokens": 0.0000015, "input_cost_per_token_priority": 0.0000015, "input_cost_per_token_above_272k_tokens_priority": 0.000003, "output_cost_per_token": 0.0000045, "output_cost_per_token_above_272k_tokens": 0.00000675, "output_cost_per_token_priority": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.0000135 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 400000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/gpt-5.4-mini-2026-03-17", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.azure.com/catalog/models/gpt-5.4-mini" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_above_272k_tokens": 1.5e-7, "cache_read_input_token_cost_priority": 1.5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 3e-7, "input_cost_per_token": 7.5e-7, "input_cost_per_token_above_272k_tokens": 0.0000015, "input_cost_per_token_priority": 0.0000015, "input_cost_per_token_above_272k_tokens_priority": 0.000003, "litellm_provider": "azure_ai", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000045, "output_cost_per_token_above_272k_tokens": 0.00000675, "output_cost_per_token_priority": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.0000135, "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/gpt-5.4-mini" ], "manual_model_modalities_note": "Azure AI exact versioned route id from official catalog." } }, { "id": "azure_ai/azure_ai/gpt-5.4-nano", "slug": "azure_ai-azure_ai-gpt-5-4-nano", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "gpt-5.4-nano", "displayName": "gpt-5.4-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.39999999999999997, "priorityOutputUsdPer1MTokens": 2.5, "priorityCachedInputUsdPer1MTokens": 0.04, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 0.39999999999999997, "above272kOutputUsdPer1MTokens": 1.875, "above272kCachedInputUsdPer1MTokens": 0.04, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-8, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "output_cost_per_token": 0.00000125, "output_cost_per_token_above_272k_tokens": 0.000001875, "output_cost_per_token_priority": 0.0000025, "output_cost_per_token_above_272k_tokens_priority": 0.00000375 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 400000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/gpt-5.4-nano", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.azure.com/catalog/models/gpt-5.4-nano" }, "rawLitellm": { "cache_read_input_token_cost": 2e-8, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "litellm_provider": "azure_ai", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000125, "output_cost_per_token_above_272k_tokens": 0.000001875, "output_cost_per_token_priority": 0.0000025, "output_cost_per_token_above_272k_tokens_priority": 0.00000375, "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/gpt-5.4-nano" ], "manual_model_modalities_note": "Azure AI exact route id from official catalog." } }, { "id": "azure_ai/azure_ai/gpt-5.4-nano-2026-03-17", "slug": "azure_ai-azure_ai-gpt-5-4-nano-2026-03-17", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "gpt-5.4-nano-2026-03-17", "displayName": "gpt-5.4-nano-2026-03-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.39999999999999997, "priorityOutputUsdPer1MTokens": 2.5, "priorityCachedInputUsdPer1MTokens": 0.04, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 0.39999999999999997, "above272kOutputUsdPer1MTokens": 1.875, "above272kCachedInputUsdPer1MTokens": 0.04, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-8, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "output_cost_per_token": 0.00000125, "output_cost_per_token_above_272k_tokens": 0.000001875, "output_cost_per_token_priority": 0.0000025, "output_cost_per_token_above_272k_tokens_priority": 0.00000375 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 400000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/gpt-5.4-nano-2026-03-17", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.azure.com/catalog/models/gpt-5.4-nano" }, "rawLitellm": { "cache_read_input_token_cost": 2e-8, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "litellm_provider": "azure_ai", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000125, "output_cost_per_token_above_272k_tokens": 0.000001875, "output_cost_per_token_priority": 0.0000025, "output_cost_per_token_above_272k_tokens_priority": 0.00000375, "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/gpt-5.4-nano" ], "manual_model_modalities_note": "Azure AI exact versioned route id from official catalog." } }, { "id": "azure_ai/azure_ai/model_router", "slug": "azure_ai-azure_ai-model_router", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "model_router", "displayName": "model_router", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.14, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.14, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/model_router", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-services/" }, "rawLitellm": { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 0, "litellm_provider": "azure_ai", "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/", "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure/azure/eu/gpt-4o-2024-08-06", "slug": "azure-azure-eu-gpt-4o-2024-08-06", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-08-06", "displayName": "gpt-4o-2024-08-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.75, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 1.375, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000001375, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-02-27" }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-4o-2024-08-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-02-27", "cache_read_input_token_cost": 0.000001375, "input_cost_per_token": 0.00000275, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000011, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure exact EU model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/eu/gpt-4o-2024-11-20", "slug": "azure-azure-eu-gpt-4o-2024-11-20", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-11-20", "displayName": "gpt-4o-2024-11-20", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.75, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": 1.38, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000138, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-03-01" }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-4o-2024-11-20", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-03-01", "cache_creation_input_token_cost": 0.00000138, "input_cost_per_token": 0.00000275, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000011, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure exact EU model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/eu/gpt-4o-mini-2024-07-18", "slug": "azure-azure-eu-gpt-4o-mini-2024-07-18", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini-2024-07-18", "displayName": "gpt-4o-mini-2024-07-18", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.165, "outputUsdPer1MTokens": 0.66, "cachedInputUsdPer1MTokens": 0.083, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.165, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 8.3e-8, "input_cost_per_token": 1.65e-7, "output_cost_per_token": 6.6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-4o-mini-2024-07-18", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 8.3e-8, "input_cost_per_token": 1.65e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure exact EU model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/eu/gpt-4o-mini-realtime-preview-2024-12-17", "slug": "azure-azure-eu-gpt-4o-mini-realtime-preview-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini-realtime-preview-2024-12-17", "displayName": "gpt-4o-mini-realtime-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.66, "outputUsdPer1MTokens": 2.64, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 11, "audioOutputUsdPer1MTokens": 22, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.66, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 3.3e-7, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_audio_token": 0.000011, "input_cost_per_token": 6.6e-7, "output_cost_per_audio_token": 0.000022, "output_cost_per_token": 0.00000264 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 3.3e-7, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_audio_token": 0.000011, "input_cost_per_token": 6.6e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.000022, "output_cost_per_token": 0.00000264, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/gpt-4o-mini-realtime-preview" ], "manual_model_modalities_note": "Azure exact EU realtime model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/eu/gpt-4o-realtime-preview-2024-10-01", "slug": "azure-azure-eu-gpt-4o-realtime-preview-2024-10-01", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-realtime-preview-2024-10-01", "displayName": "gpt-4o-realtime-preview-2024-10-01", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 22, "cachedInputUsdPer1MTokens": 2.75, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 110, "audioOutputUsdPer1MTokens": 220, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 0.000022, "cache_read_input_token_cost": 0.00000275, "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 0.0000055, "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 0.000022 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-4o-realtime-preview-2024-10-01", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 0.000022, "cache_read_input_token_cost": 0.00000275, "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 0.0000055, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 0.000022, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/gpt-4o-realtime-preview" ], "manual_model_modalities_note": "Azure exact EU realtime model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/eu/gpt-4o-realtime-preview-2024-12-17", "slug": "azure-azure-eu-gpt-4o-realtime-preview-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-realtime-preview-2024-12-17", "displayName": "gpt-4o-realtime-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 22, "cachedInputUsdPer1MTokens": 2.75, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 44, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_audio_token_cost": 0.0000025, "cache_read_input_token_cost": 0.00000275, "input_cost_per_audio_token": 0.000044, "input_cost_per_token": 0.0000055, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.000022 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-4o-realtime-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_audio_token_cost": 0.0000025, "cache_read_input_token_cost": 0.00000275, "input_cost_per_audio_token": 0.000044, "input_cost_per_token": 0.0000055, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.000022, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/eu/gpt-5-2025-08-07", "slug": "azure-azure-eu-gpt-5-2025-08-07", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-2025-08-07", "displayName": "gpt-5-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.375, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 0.1375, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.375, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.375e-7, "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-5-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.375e-7, "input_cost_per_token": 0.000001375, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000011, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "azure/azure/eu/gpt-5-mini-2025-08-07", "slug": "azure-azure-eu-gpt-5-mini-2025-08-07", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-mini-2025-08-07", "displayName": "gpt-5-mini-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.275, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.0275, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.275, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.75e-8, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-5-mini-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.75e-8, "input_cost_per_token": 2.75e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000022, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "azure/azure/eu/gpt-5.1", "slug": "azure-azure-eu-gpt-5-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1", "displayName": "gpt-5.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.38, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 0.14, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "none_reasoning_effort": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-5.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000011, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/eu/gpt-5.1-chat", "slug": "azure-azure-eu-gpt-5-1-chat", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-chat", "displayName": "gpt-5.1-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.38, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 0.14, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "none_reasoning_effort": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-5.1-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000011, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/eu/gpt-5.1-codex", "slug": "azure-azure-eu-gpt-5-1-codex", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex", "displayName": "gpt-5.1-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.38, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 0.14, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-5.1-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000011, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/eu/gpt-5.1-codex-mini", "slug": "azure-azure-eu-gpt-5-1-codex-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex-mini", "displayName": "gpt-5.1-codex-mini", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 0.275, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.028, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.275, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-5.1-codex-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.75e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.0000022, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/eu/gpt-5-nano-2025-08-07", "slug": "azure-azure-eu-gpt-5-nano-2025-08-07", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-nano-2025-08-07", "displayName": "gpt-5-nano-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.055, "outputUsdPer1MTokens": 0.44, "cachedInputUsdPer1MTokens": 0.0055, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.055, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.5e-9, "input_cost_per_token": 5.5e-8, "output_cost_per_token": 4.4e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/gpt-5-nano-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.5e-9, "input_cost_per_token": 5.5e-8, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "aime2025_accuracy_gpt5nanohigh_officiallaunchpost_28": { "label": "AIME 2025", "category": "reasoning", "score": 85.2, "scoreText": "85.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-nano", "exactModelOrSnapshot": "GPT-5 nano (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." } } }, { "id": "azure/azure/eu/o1-2024-12-17", "slug": "azure-azure-eu-o1-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "o1-2024-12-17", "displayName": "o1-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 16.5, "outputUsdPer1MTokens": 66, "cachedInputUsdPer1MTokens": 8.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 16.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000825, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.000066 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/o1-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000825, "input_cost_per_token": 0.0000165, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000066, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/o1" ], "manual_model_modalities_note": "Azure exact EU reasoning model id from official docs." } }, { "id": "azure/azure/eu/o1-mini-2024-09-12", "slug": "azure-azure-eu-o1-mini-2024-09-12", "provider": "Azure", "providerSlug": "azure", "name": "o1-mini-2024-09-12", "displayName": "o1-mini-2024-09-12", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.21, "outputUsdPer1MTokens": 4.84, "cachedInputUsdPer1MTokens": 0.605, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.605, "batchOutputUsdPer1MTokens": 2.42, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "input_cost_per_token_batches": 6.05e-7, "output_cost_per_token": 0.00000484, "output_cost_per_token_batches": 0.00000242 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 128000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/o1-mini-2024-09-12", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "input_cost_per_token_batches": 6.05e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.00000484, "output_cost_per_token_batches": 0.00000242, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/o1-mini" ], "manual_model_modalities_note": "Azure exact EU reasoning model id from official docs." } }, { "id": "azure/azure/eu/o1-preview-2024-09-12", "slug": "azure-azure-eu-o1-preview-2024-09-12", "provider": "Azure", "providerSlug": "azure", "name": "o1-preview-2024-09-12", "displayName": "o1-preview-2024-09-12", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 16.5, "outputUsdPer1MTokens": 66, "cachedInputUsdPer1MTokens": 8.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 16.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000825, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.000066 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 128000, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/o1-preview-2024-09-12", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000825, "input_cost_per_token": 0.0000165, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000066, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions", "https://ai.azure.com/catalog/models/o1-preview" ], "manual_model_modalities_note": "Azure exact EU reasoning model id from official docs." } }, { "id": "azure/azure/eu/o3-mini-2025-01-31", "slug": "azure-azure-eu-o3-mini-2025-01-31", "provider": "Azure", "providerSlug": "azure", "name": "o3-mini-2025-01-31", "displayName": "o3-mini-2025-01-31", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.21, "outputUsdPer1MTokens": 4.84, "cachedInputUsdPer1MTokens": 0.605, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.605, "batchOutputUsdPer1MTokens": 2.42, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "input_cost_per_token_batches": 6.05e-7, "output_cost_per_token": 0.00000484, "output_cost_per_token_batches": 0.00000242 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/eu/o3-mini-2025-01-31", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "input_cost_per_token_batches": 6.05e-7, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00000484, "output_cost_per_token_batches": 0.00000242, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions", "https://learn.microsoft.com/en-us/azure/foundry/openai/whats-new" ], "manual_model_modalities_note": "Azure exact EU reasoning model id from official docs." }, "benchmarks": { "aime2024_accuracy_o3minihigh_officiallaunchpost_18": { "label": "AIME 2024", "category": "reasoning", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "gpqadiamond_accuracy_o3minihigh_officiallaunchpost_19": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 77, "scoreText": "77.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "swebenchverified_accuracy_o3minihigh_officiallaunchpost_20": { "label": "SWE-bench Verified", "category": "coding", "score": 48.9, "scoreText": "48.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; n=477 verified tasks." } } }, { "id": "azure/azure/global-standard/gpt-4o-2024-08-06", "slug": "azure-azure-global-standard-gpt-4o-2024-08-06", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-08-06", "displayName": "gpt-4o-2024-08-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-02-27" }, "source": { "type": "litellm", "litellmKey": "azure/global-standard/gpt-4o-2024-08-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000125, "deprecation_date": "2026-02-27", "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4o exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/global-standard/gpt-4o-2024-11-20", "slug": "azure-azure-global-standard-gpt-4o-2024-11-20", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-11-20", "displayName": "gpt-4o-2024-11-20", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-03-01" }, "source": { "type": "litellm", "litellmKey": "azure/global-standard/gpt-4o-2024-11-20", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000125, "deprecation_date": "2026-03-01", "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4o exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/global-standard/gpt-4o-mini", "slug": "azure-azure-global-standard-gpt-4o-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini", "displayName": "gpt-4o-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/global-standard/gpt-4o-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4o exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/global/gpt-4o-2024-08-06", "slug": "azure-azure-global-gpt-4o-2024-08-06", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-08-06", "displayName": "gpt-4o-2024-08-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-02-27" }, "source": { "type": "litellm", "litellmKey": "azure/global/gpt-4o-2024-08-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-02-27", "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions" ], "manual_model_modalities_note": "Azure exact global model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/global/gpt-4o-2024-11-20", "slug": "azure-azure-global-gpt-4o-2024-11-20", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-11-20", "displayName": "gpt-4o-2024-11-20", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-03-01" }, "source": { "type": "litellm", "litellmKey": "azure/global/gpt-4o-2024-11-20", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-03-01", "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions" ], "manual_model_modalities_note": "Azure exact global model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/global/gpt-5.1", "slug": "azure-azure-global-gpt-5-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1", "displayName": "gpt-5.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "none_reasoning_effort": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/global/gpt-5.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/global/gpt-5.1-chat", "slug": "azure-azure-global-gpt-5-1-chat", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-chat", "displayName": "gpt-5.1-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "none_reasoning_effort": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/global/gpt-5.1-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/global/gpt-5.1-codex", "slug": "azure-azure-global-gpt-5-1-codex", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex", "displayName": "gpt-5.1-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/global/gpt-5.1-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/global/gpt-5.1-codex-mini", "slug": "azure-azure-global-gpt-5-1-codex-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex-mini", "displayName": "gpt-5.1-codex-mini", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/global/gpt-5.1-codex-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000002, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/gpt-3.5-turbo", "slug": "azure-azure-gpt-3-5-turbo", "provider": "Azure", "providerSlug": "azure", "name": "gpt-3.5-turbo", "displayName": "gpt-3.5-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4097, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-3.5-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions", "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-3.5-turbo-0125", "slug": "azure-azure-gpt-3-5-turbo-0125", "provider": "Azure", "providerSlug": "azure", "name": "gpt-3.5-turbo-0125", "displayName": "gpt-3.5-turbo-0125", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2025-03-31" }, "source": { "type": "litellm", "litellmKey": "azure/gpt-3.5-turbo-0125", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2025-03-31", "input_cost_per_token": 5e-7, "litellm_provider": "azure", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions", "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/json-mode?view=foundry-classic" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure_text/azure/gpt-3.5-turbo-instruct-0914", "slug": "azure_text-azure-gpt-3-5-turbo-instruct-0914", "provider": "azure_text", "providerSlug": "azure_text", "name": "gpt-3.5-turbo-instruct-0914", "displayName": "gpt-3.5-turbo-instruct-0914", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4097, "maxInputTokens": 4097, "maxOutputTokens": null, "maxTokens": 4097, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-3.5-turbo-instruct-0914", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000015, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", "output_cost_per_token": 0.000002 } }, { "id": "azure/azure/gpt-35-turbo", "slug": "azure-azure-gpt-35-turbo", "provider": "Azure", "providerSlug": "azure", "name": "gpt-35-turbo", "displayName": "gpt-35-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4097, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-35-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" ], "manual_model_modalities_note": "Azure GPT-35 exact ids from official model tables" } }, { "id": "azure/azure/gpt-35-turbo-0125", "slug": "azure-azure-gpt-35-turbo-0125", "provider": "Azure", "providerSlug": "azure", "name": "gpt-35-turbo-0125", "displayName": "gpt-35-turbo-0125", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2025-05-31" }, "source": { "type": "litellm", "litellmKey": "azure/gpt-35-turbo-0125", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2025-05-31", "input_cost_per_token": 5e-7, "litellm_provider": "azure", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" ], "manual_model_modalities_note": "Azure GPT-35 exact ids from official model tables" } }, { "id": "azure/azure/gpt-35-turbo-1106", "slug": "azure-azure-gpt-35-turbo-1106", "provider": "Azure", "providerSlug": "azure", "name": "gpt-35-turbo-1106", "displayName": "gpt-35-turbo-1106", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2025-03-31" }, "source": { "type": "litellm", "litellmKey": "azure/gpt-35-turbo-1106", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2025-03-31", "input_cost_per_token": 0.000001, "litellm_provider": "azure", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" ], "manual_model_modalities_note": "Azure GPT-35 exact ids from official model tables" } }, { "id": "azure/azure/gpt-35-turbo-16k", "slug": "azure-azure-gpt-35-turbo-16k", "provider": "Azure", "providerSlug": "azure", "name": "gpt-35-turbo-16k", "displayName": "gpt-35-turbo-16k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-35-turbo-16k", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "azure", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000004, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions", "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/legacy-models" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-35-turbo-16k-0613", "slug": "azure-azure-gpt-35-turbo-16k-0613", "provider": "Azure", "providerSlug": "azure", "name": "gpt-35-turbo-16k-0613", "displayName": "gpt-35-turbo-16k-0613", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-35-turbo-16k-0613", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "azure", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000004, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" ], "manual_model_modalities_note": "Azure GPT-35 exact ids from official model tables" } }, { "id": "azure_text/azure/gpt-35-turbo-instruct", "slug": "azure_text-azure-gpt-35-turbo-instruct", "provider": "azure_text", "providerSlug": "azure_text", "name": "gpt-35-turbo-instruct", "displayName": "gpt-35-turbo-instruct", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4097, "maxInputTokens": 4097, "maxOutputTokens": null, "maxTokens": 4097, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-35-turbo-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000015, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", "output_cost_per_token": 0.000002 } }, { "id": "azure_text/azure/gpt-35-turbo-instruct-0914", "slug": "azure_text-azure-gpt-35-turbo-instruct-0914", "provider": "azure_text", "providerSlug": "azure_text", "name": "gpt-35-turbo-instruct-0914", "displayName": "gpt-35-turbo-instruct-0914", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4097, "maxInputTokens": 4097, "maxOutputTokens": null, "maxTokens": 4097, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-35-turbo-instruct-0914", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000015, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", "output_cost_per_token": 0.000002 } }, { "id": "azure/azure/gpt-4", "slug": "azure-azure-gpt-4", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4", "displayName": "gpt-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00003, "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions", "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/gpt-with-vision" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-4-0125-preview", "slug": "azure-azure-gpt-4-0125-preview", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4-0125-preview", "displayName": "gpt-4-0125-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4-0125-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/gpt-with-vision", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-4-0613", "slug": "azure-azure-gpt-4-0613", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4-0613", "displayName": "gpt-4-0613", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4-0613", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00003, "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-services/openai/faq?view=azureml-api-2", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-4-1106-preview", "slug": "azure-azure-gpt-4-1106-preview", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4-1106-preview", "displayName": "gpt-4-1106-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4-1106-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-services/openai/faq?view=azureml-api-2", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-4-32k", "slug": "azure-azure-gpt-4-32k", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4-32k", "displayName": "gpt-4-32k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 60, "outputUsdPer1MTokens": 120, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 60, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00006, "output_cost_per_token": 0.00012 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4-32k", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00006, "litellm_provider": "azure", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00012, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-services/openai/faq?view=azureml-api-2", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-4-32k-0613", "slug": "azure-azure-gpt-4-32k-0613", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4-32k-0613", "displayName": "gpt-4-32k-0613", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 60, "outputUsdPer1MTokens": 120, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 60, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00006, "output_cost_per_token": 0.00012 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4-32k-0613", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00006, "litellm_provider": "azure", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00012, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-services/openai/faq?view=azureml-api-2", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-4-turbo", "slug": "azure-azure-gpt-4-turbo", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4-turbo", "displayName": "gpt-4-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions", "https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/gpt-with-vision?tabs=python" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-4-turbo-2024-04-09", "slug": "azure-azure-gpt-4-turbo-2024-04-09", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4-turbo-2024-04-09", "displayName": "gpt-4-turbo-2024-04-09", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4-turbo-2024-04-09", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4 Turbo with Vision exact snapshot" } }, { "id": "azure/azure/gpt-4-turbo-vision-preview", "slug": "azure-azure-gpt-4-turbo-vision-preview", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4-turbo-vision-preview", "displayName": "gpt-4-turbo-vision-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4-turbo-vision-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions", "https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/gpt-with-vision?tabs=python" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-4.1", "slug": "azure-azure-gpt-4-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4.1", "displayName": "gpt-4.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 4, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4.1 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "azure/azure/gpt-4.1-2025-04-14", "slug": "azure-azure-gpt-4-1-2025-04-14", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4.1-2025-04-14", "displayName": "gpt-4.1-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 4, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": "2026-11-04" }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4.1-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4.1 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "azure/azure/gpt-4.1-mini", "slug": "azure-azure-gpt-4-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4.1-mini", "displayName": "gpt-4.1-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.19999999999999998, "batchOutputUsdPer1MTokens": 0.7999999999999999, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 4e-7, "input_cost_per_token_batches": 2e-7, "output_cost_per_token": 0.0000016, "output_cost_per_token_batches": 8e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4.1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 4e-7, "input_cost_per_token_batches": 2e-7, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000016, "output_cost_per_token_batches": 8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4.1 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt41mini_officiallaunchpost_5": { "label": "SWE-bench Verified", "category": "coding", "score": 23.6, "scoreText": "23.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-mini", "exactModelOrSnapshot": "GPT-4.1 mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table for the GPT-4.1 family." } } }, { "id": "azure/azure/gpt-4.1-mini-2025-04-14", "slug": "azure-azure-gpt-4-1-mini-2025-04-14", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4.1-mini-2025-04-14", "displayName": "gpt-4.1-mini-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.19999999999999998, "batchOutputUsdPer1MTokens": 0.7999999999999999, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 4e-7, "input_cost_per_token_batches": 2e-7, "output_cost_per_token": 0.0000016, "output_cost_per_token_batches": 8e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": "2026-11-04" }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4.1-mini-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 4e-7, "input_cost_per_token_batches": 2e-7, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000016, "output_cost_per_token_batches": 8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4.1 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt41mini_officiallaunchpost_5": { "label": "SWE-bench Verified", "category": "coding", "score": 23.6, "scoreText": "23.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-mini", "exactModelOrSnapshot": "GPT-4.1 mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table for the GPT-4.1 family." } } }, { "id": "azure/azure/gpt-4.1-nano", "slug": "azure-azure-gpt-4-1-nano", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4.1-nano", "displayName": "gpt-4.1-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.049999999999999996, "batchOutputUsdPer1MTokens": 0.19999999999999998, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, "input_cost_per_token_batches": 5e-8, "output_cost_per_token": 4e-7, "output_cost_per_token_batches": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4.1-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, "input_cost_per_token_batches": 5e-8, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-7, "output_cost_per_token_batches": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4.1 exact ids from official model tables" }, "benchmarks": { "aime24_accuracy_gpt41nano_officiallaunchpost_6": { "label": "AIME 2024", "category": "reasoning", "score": 29.4, "scoreText": "29.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-nano", "exactModelOrSnapshot": "GPT-4.1 nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Academic-knowledge appendix comparison row for the nano model." }, "mmlu_accuracy_gpt41nano_officiallaunchpost_258": { "label": "MMLU", "category": "general_knowledge", "score": 80.1, "scoreText": "80.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the narrative and table." }, "gpqa_accuracy_gpt41nano_officiallaunchpost_259": { "label": "GPQA", "category": "reasoning", "score": 50.3, "scoreText": "50.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." }, "aiderpolyglotcoding_passrate_gpt41nano_officiallaunchpost_260": { "label": "Aider Polyglot", "category": "coding", "score": 9.8, "scoreText": "9.8%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." } } }, { "id": "azure/azure/gpt-4.1-nano-2025-04-14", "slug": "azure-azure-gpt-4-1-nano-2025-04-14", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4.1-nano-2025-04-14", "displayName": "gpt-4.1-nano-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.049999999999999996, "batchOutputUsdPer1MTokens": 0.19999999999999998, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, "input_cost_per_token_batches": 5e-8, "output_cost_per_token": 4e-7, "output_cost_per_token_batches": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": "2026-11-04" }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4.1-nano-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, "input_cost_per_token_batches": 5e-8, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-7, "output_cost_per_token_batches": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4.1 exact ids from official model tables" }, "benchmarks": { "aime24_accuracy_gpt41nano_officiallaunchpost_6": { "label": "AIME 2024", "category": "reasoning", "score": 29.4, "scoreText": "29.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-nano", "exactModelOrSnapshot": "GPT-4.1 nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Academic-knowledge appendix comparison row for the nano model." }, "mmlu_accuracy_gpt41nano_officiallaunchpost_258": { "label": "MMLU", "category": "general_knowledge", "score": 80.1, "scoreText": "80.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the narrative and table." }, "gpqa_accuracy_gpt41nano_officiallaunchpost_259": { "label": "GPQA", "category": "reasoning", "score": 50.3, "scoreText": "50.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." }, "aiderpolyglotcoding_passrate_gpt41nano_officiallaunchpost_260": { "label": "Aider Polyglot", "category": "coding", "score": 9.8, "scoreText": "9.8%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." } } }, { "id": "azure/azure/gpt-4.5-preview", "slug": "azure-azure-gpt-4-5-preview", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4.5-preview", "displayName": "gpt-4.5-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 75, "outputUsdPer1MTokens": 150, "cachedInputUsdPer1MTokens": 37.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 37.5, "batchOutputUsdPer1MTokens": 75, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000375, "input_cost_per_token": 0.000075, "input_cost_per_token_batches": 0.0000375, "output_cost_per_token": 0.00015, "output_cost_per_token_batches": 0.000075 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4.5-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000375, "input_cost_per_token": 0.000075, "input_cost_per_token_batches": 0.0000375, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00015, "output_cost_per_token_batches": 0.000075, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/gpt-with-vision?view=foundry-classic" ], "manual_model_modalities_note": "Azure exact model id from official docs." } }, { "id": "azure/azure/gpt-4o", "slug": "azure-azure-gpt-4o", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o", "displayName": "gpt-4o", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4o exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/gpt-4o-2024-05-13", "slug": "azure-azure-gpt-4o-2024-05-13", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-05-13", "displayName": "gpt-4o-2024-05-13", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-2024-05-13", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4o exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/gpt-4o-2024-08-06", "slug": "azure-azure-gpt-4o-2024-08-06", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-08-06", "displayName": "gpt-4o-2024-08-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-02-27" }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-2024-08-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-02-27", "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4o exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/gpt-4o-2024-11-20", "slug": "azure-azure-gpt-4o-2024-11-20", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-11-20", "displayName": "gpt-4o-2024-11-20", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.75, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-03-01" }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-2024-11-20", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-03-01", "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.00000275, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000011, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4o exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/gpt-audio-2025-08-28", "slug": "azure-azure-gpt-audio-2025-08-28", "provider": "Azure", "providerSlug": "azure", "name": "gpt-audio-2025-08-28", "displayName": "gpt-audio-2025-08-28", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-audio-2025-08-28", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false } }, { "id": "azure/azure/gpt-audio-1.5-2026-02-23", "slug": "azure-azure-gpt-audio-1-5-2026-02-23", "provider": "Azure", "providerSlug": "azure", "name": "gpt-audio-1.5-2026-02-23", "displayName": "gpt-audio-1.5-2026-02-23", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-audio-1.5-2026-02-23", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false } }, { "id": "azure/azure/gpt-audio-mini-2025-10-06", "slug": "azure-azure-gpt-audio-mini-2025-10-06", "provider": "Azure", "providerSlug": "azure", "name": "gpt-audio-mini-2025-10-06", "displayName": "gpt-audio-mini-2025-10-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-audio-mini-2025-10-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false } }, { "id": "azure/azure/gpt-4o-audio-preview-2024-12-17", "slug": "azure-azure-gpt-4o-audio-preview-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-audio-preview-2024-12-17", "displayName": "gpt-4o-audio-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-audio-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/gpt-4o-mini", "slug": "azure-azure-gpt-4o-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini", "displayName": "gpt-4o-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.165, "outputUsdPer1MTokens": 0.66, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.165, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.65e-7, "output_cost_per_token": 6.6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.65e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4o exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/gpt-4o-mini-2024-07-18", "slug": "azure-azure-gpt-4o-mini-2024-07-18", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini-2024-07-18", "displayName": "gpt-4o-mini-2024-07-18", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.165, "outputUsdPer1MTokens": 0.66, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.165, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.65e-7, "output_cost_per_token": 6.6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-mini-2024-07-18", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.65e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-4o exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/gpt-4o-mini-audio-preview-2024-12-17", "slug": "azure-azure-gpt-4o-mini-audio-preview-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini-audio-preview-2024-12-17", "displayName": "gpt-4o-mini-audio-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-mini-audio-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/gpt-4o-mini-realtime-preview-2024-12-17", "slug": "azure-azure-gpt-4o-mini-realtime-preview-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini-realtime-preview-2024-12-17", "displayName": "gpt-4o-mini-realtime-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "audio" ], "input": [ "audio" ], "output": [ "audio" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-mini-realtime-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=standard%2Cstandard-chat-completions", "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/realtime-audio-quickstart" ], "manual_model_modalities_note": "Azure exact realtime model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/gpt-realtime-2025-08-28", "slug": "azure-azure-gpt-realtime-2025-08-28", "provider": "Azure", "providerSlug": "azure", "name": "gpt-realtime-2025-08-28", "displayName": "gpt-realtime-2025-08-28", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 4, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": 4, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 32, "audioOutputUsdPer1MTokens": 64, "imageInputUsdPer1MUnits": 5, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 0.000004, "cache_read_input_token_cost": 0.000004, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-realtime-2025-08-28", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 0.000004, "cache_read_input_token_cost": 0.000004, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "azure/azure/gpt-realtime-1.5-2026-02-23", "slug": "azure-azure-gpt-realtime-1-5-2026-02-23", "provider": "Azure", "providerSlug": "azure", "name": "gpt-realtime-1.5-2026-02-23", "displayName": "gpt-realtime-1.5-2026-02-23", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 4, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": 4, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 32, "audioOutputUsdPer1MTokens": 64, "imageInputUsdPer1MUnits": 5, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 0.000004, "cache_read_input_token_cost": 0.000004, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-realtime-1.5-2026-02-23", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 0.000004, "cache_read_input_token_cost": 0.000004, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "azure/azure/gpt-realtime-mini-2025-10-06", "slug": "azure-azure-gpt-realtime-mini-2025-10-06", "provider": "Azure", "providerSlug": "azure", "name": "gpt-realtime-mini-2025-10-06", "displayName": "gpt-realtime-mini-2025-10-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": 0.06, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": 0.7999999999999999, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 6e-8, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-realtime-mini-2025-10-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 6e-8, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "input_cost_per_token": 6e-7, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "azure/azure/gpt-4o-mini-transcribe", "slug": "azure-azure-gpt-4o-mini-transcribe", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini-transcribe", "displayName": "gpt-4o-mini-transcribe", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1.25, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": null, "maxInputTokens": 16000, "maxOutputTokens": 2000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-mini-transcribe", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 0.000005, "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/gpt-4o-mini-tts", "slug": "azure-azure-gpt-4o-mini-tts", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini-tts", "displayName": "gpt-4o-mini-tts", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": 12, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.00025, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "audio" ] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-mini-tts", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "mode": "audio_speech", "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ] }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/gpt-4o-realtime-preview-2024-10-01", "slug": "azure-azure-gpt-4o-realtime-preview-2024-10-01", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-realtime-preview-2024-10-01", "displayName": "gpt-4o-realtime-preview-2024-10-01", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 20, "cachedInputUsdPer1MTokens": 2.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 100, "audioOutputUsdPer1MTokens": 200, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 0.00002, "cache_read_input_token_cost": 0.0000025, "input_cost_per_audio_token": 0.0001, "input_cost_per_token": 0.000005, "output_cost_per_audio_token": 0.0002, "output_cost_per_token": 0.00002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "audio" ], "input": [ "audio" ], "output": [ "audio" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-realtime-preview-2024-10-01", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 0.00002, "cache_read_input_token_cost": 0.0000025, "input_cost_per_audio_token": 0.0001, "input_cost_per_token": 0.000005, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.0002, "output_cost_per_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/realtime-audio-quickstart" ], "manual_model_modalities_note": "Azure exact realtime model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/gpt-4o-realtime-preview-2024-12-17", "slug": "azure-azure-gpt-4o-realtime-preview-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-realtime-preview-2024-12-17", "displayName": "gpt-4o-realtime-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 20, "cachedInputUsdPer1MTokens": 2.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.000005, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-realtime-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.000005, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00002, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/gpt-4o-transcribe", "slug": "azure-azure-gpt-4o-transcribe", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-transcribe", "displayName": "gpt-4o-transcribe", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 2.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.0000025, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": null, "maxInputTokens": 16000, "maxOutputTokens": 2000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-transcribe", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.0000025, "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/gpt-4o-transcribe-diarize", "slug": "azure-azure-gpt-4o-transcribe-diarize", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-transcribe-diarize", "displayName": "gpt-4o-transcribe-diarize", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 2.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.0000025, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": null, "maxInputTokens": 16000, "maxOutputTokens": 2000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-4o-transcribe-diarize", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.0000025, "input_cost_per_token": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/gpt-5.1-2025-11-13", "slug": "azure-azure-gpt-5-1-2025-11-13", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-2025-11-13", "displayName": "gpt-5.1-2025-11-13", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.5, "priorityOutputUsdPer1MTokens": 20, "priorityCachedInputUsdPer1MTokens": 0.25, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "none_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.1-2025-11-13", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_none_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-5.1 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/gpt-5.1-chat-2025-11-13", "slug": "azure-azure-gpt-5-1-chat-2025-11-13", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-chat-2025-11-13", "displayName": "gpt-5.1-chat-2025-11-13", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.5, "priorityOutputUsdPer1MTokens": 20, "priorityCachedInputUsdPer1MTokens": 0.25, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "native_streaming": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": false, "vision": true, "none_reasoning_effort": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.1-chat-2025-11-13", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_vision": true, "supports_none_reasoning_effort": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/gpt-5.1-codex-2025-11-13", "slug": "azure-azure-gpt-5-1-codex-2025-11-13", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex-2025-11-13", "displayName": "gpt-5.1-codex-2025-11-13", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.5, "priorityOutputUsdPer1MTokens": 20, "priorityCachedInputUsdPer1MTokens": 0.25, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.1-codex-2025-11-13", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/gpt-5.1-codex-mini-2025-11-13", "slug": "azure-azure-gpt-5-1-codex-mini-2025-11-13", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex-mini-2025-11-13", "displayName": "gpt-5.1-codex-mini-2025-11-13", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.44999999999999996, "priorityOutputUsdPer1MTokens": 3.5999999999999996, "priorityCachedInputUsdPer1MTokens": 0.045, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token": 2.5e-7, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_token": 0.000002, "output_cost_per_token_priority": 0.0000036 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.1-codex-mini-2025-11-13", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token": 2.5e-7, "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000002, "output_cost_per_token_priority": 0.0000036, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/gpt-5", "slug": "azure-azure-gpt-5", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5", "displayName": "gpt-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-5 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "azure/azure/gpt-5-2025-08-07", "slug": "azure-azure-gpt-5-2025-08-07", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-2025-08-07", "displayName": "gpt-5-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-5 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "azure/azure/gpt-5-chat", "slug": "azure-azure-gpt-5-chat", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-chat", "displayName": "gpt-5-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5-chat", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-5 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "azure/azure/gpt-5-chat-latest", "slug": "azure-azure-gpt-5-chat-latest", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-chat-latest", "displayName": "gpt-5-chat-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5-chat-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "azure/azure/gpt-5-codex", "slug": "azure-azure-gpt-5-codex", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-codex", "displayName": "gpt-5-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "azure/azure/gpt-5-mini", "slug": "azure-azure-gpt-5-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-mini", "displayName": "gpt-5-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000002, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-5 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "azure/azure/gpt-5-mini-2025-08-07", "slug": "azure-azure-gpt-5-mini-2025-08-07", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-mini-2025-08-07", "displayName": "gpt-5-mini-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5-mini-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000002, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-5 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "azure/azure/gpt-5-nano", "slug": "azure-azure-gpt-5-nano", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-nano", "displayName": "gpt-5-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.005, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-9, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-9, "input_cost_per_token": 5e-8, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-5 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "aime2025_accuracy_gpt5nanohigh_officiallaunchpost_28": { "label": "AIME 2025", "category": "reasoning", "score": 85.2, "scoreText": "85.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-nano", "exactModelOrSnapshot": "GPT-5 nano (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." } } }, { "id": "azure/azure/gpt-5-nano-2025-08-07", "slug": "azure-azure-gpt-5-nano-2025-08-07", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-nano-2025-08-07", "displayName": "gpt-5-nano-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.005, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-9, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5-nano-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-9, "input_cost_per_token": 5e-8, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-5 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "aime2025_accuracy_gpt5nanohigh_officiallaunchpost_28": { "label": "AIME 2025", "category": "reasoning", "score": 85.2, "scoreText": "85.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-nano", "exactModelOrSnapshot": "GPT-5 nano (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." } } }, { "id": "azure/azure/gpt-5-pro", "slug": "azure-azure-gpt-5-pro", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-pro", "displayName": "gpt-5-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 120, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00012 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5" }, "rawLitellm": { "input_cost_per_token": 0.000015, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "azure/azure/gpt-5.1", "slug": "azure-azure-gpt-5-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1", "displayName": "gpt-5.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "none_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure GPT-5.1 exact ids from official model tables" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/gpt-5.1-chat", "slug": "azure-azure-gpt-5-1-chat", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-chat", "displayName": "gpt-5.1-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "none_reasoning_effort": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.1-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/gpt-5.1-codex", "slug": "azure-azure-gpt-5-1-codex", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex", "displayName": "gpt-5.1-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.1-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/gpt-5.1-codex-max", "slug": "azure-azure-gpt-5-1-codex-max", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex-max", "displayName": "gpt-5.1-codex-max", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.1-codex-max", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/gpt-5.1-codex-mini", "slug": "azure-azure-gpt-5-1-codex-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex-mini", "displayName": "gpt-5.1-codex-mini", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.1-codex-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000002, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/gpt-5.2", "slug": "azure-azure-gpt-5-2", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.2", "displayName": "gpt-5.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000014, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "azure/azure/gpt-5.2-2025-12-11", "slug": "azure-azure-gpt-5-2-2025-12-11", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.2-2025-12-11", "displayName": "gpt-5.2-2025-12-11", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 28, "priorityCachedInputUsdPer1MTokens": 0.35, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.2-2025-12-11", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "azure/azure/gpt-5.2-chat", "slug": "azure-azure-gpt-5-2-chat", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.2-chat", "displayName": "gpt-5.2-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 28, "priorityCachedInputUsdPer1MTokens": 0.35, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.2-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "azure/azure/gpt-5.2-chat-2025-12-11", "slug": "azure-azure-gpt-5-2-chat-2025-12-11", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.2-chat-2025-12-11", "displayName": "gpt-5.2-chat-2025-12-11", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 28, "priorityCachedInputUsdPer1MTokens": 0.35, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.2-chat-2025-12-11", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "azure/azure/gpt-5.2-codex", "slug": "azure-azure-gpt-5-2-codex", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.2-codex", "displayName": "gpt-5.2-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.2-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000014, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "azure/azure/gpt-5.3-chat", "slug": "azure-azure-gpt-5-3-chat", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.3-chat", "displayName": "gpt-5.3-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 28, "priorityCachedInputUsdPer1MTokens": 0.35, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.3-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true } }, { "id": "azure/azure/gpt-5.3-codex", "slug": "azure-azure-gpt-5-3-codex", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.3-codex", "displayName": "gpt-5.3-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.3-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000014, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure/azure/gpt-5.2-pro", "slug": "azure-azure-gpt-5-2-pro", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.2-pro", "displayName": "gpt-5.2-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 21, "outputUsdPer1MTokens": 168, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.2-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000021, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure/azure/gpt-5.2-pro-2025-12-11", "slug": "azure-azure-gpt-5-2-pro-2025-12-11", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.2-pro-2025-12-11", "displayName": "gpt-5.2-pro-2025-12-11", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 21, "outputUsdPer1MTokens": 168, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.2-pro-2025-12-11", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000021, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure/azure/gpt-5.4", "slug": "azure-azure-gpt-5-4", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.4", "displayName": "gpt-5.4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 5, "priorityOutputUsdPer1MTokens": 30, "priorityCachedInputUsdPer1MTokens": 0.5, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 5, "above272kOutputUsdPer1MTokens": 22.5, "above272kCachedInputUsdPer1MTokens": 0.5, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.4", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true }, "benchmarks": { "livebench_livebenchscore_gpt54thinkingxhigheffort_benchmarkleaderboard_228": { "label": "LiveBench", "category": "general_knowledge", "score": 80.28, "scoreText": "80.28", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "GPT-5.4 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt54high_benchmarkleaderboard_244": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1483, "scoreText": "1483±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "gpt-5.4-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." } } }, { "id": "azure/azure/gpt-5.4-2026-03-05", "slug": "azure-azure-gpt-5-4-2026-03-05", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.4-2026-03-05", "displayName": "gpt-5.4-2026-03-05", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 5, "priorityOutputUsdPer1MTokens": 30, "priorityCachedInputUsdPer1MTokens": 0.5, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 5, "above272kOutputUsdPer1MTokens": 22.5, "above272kCachedInputUsdPer1MTokens": 0.5, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.4-2026-03-05", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true }, "benchmarks": { "livebench_livebenchscore_gpt54thinkingxhigheffort_benchmarkleaderboard_228": { "label": "LiveBench", "category": "general_knowledge", "score": 80.28, "scoreText": "80.28", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "GPT-5.4 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt54high_benchmarkleaderboard_244": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1483, "scoreText": "1483±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "gpt-5.4-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." } } }, { "id": "azure/azure/gpt-5.4-pro", "slug": "azure-azure-gpt-5-4-pro", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.4-pro", "displayName": "gpt-5.4-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 180, "cachedInputUsdPer1MTokens": 3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 60, "above272kOutputUsdPer1MTokens": 270, "above272kCachedInputUsdPer1MTokens": 6, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.4-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure/azure/gpt-5.4-pro-2026-03-05", "slug": "azure-azure-gpt-5-4-pro-2026-03-05", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.4-pro-2026-03-05", "displayName": "gpt-5.4-pro-2026-03-05", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 180, "cachedInputUsdPer1MTokens": 3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 60, "above272kOutputUsdPer1MTokens": 270, "above272kCachedInputUsdPer1MTokens": 6, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.4-pro-2026-03-05", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure/azure/gpt-5.5", "slug": "azure-azure-gpt-5-5", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.5", "displayName": "gpt-5.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 10, "priorityOutputUsdPer1MTokens": 60, "priorityCachedInputUsdPer1MTokens": 1, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 10, "above272kOutputUsdPer1MTokens": 45, "above272kCachedInputUsdPer1MTokens": 1, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "output_cost_per_token": 0.00003, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00003, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "benchmarks": { "livebench_livebenchscore_gpt55thinkingxhigheffort_benchmarkleaderboard_227": { "label": "LiveBench", "category": "general_knowledge", "score": 80.71, "scoreText": "80.71", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt55high_benchmarkleaderboard_242": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1487, "scoreText": "1487±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "gpt-5.5-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." }, "gpqadiamond_accuracy_gpt55xhigh_benchmarkleaderboard_246": { "label": "GPQA Diamond", "category": "science", "score": 93.5, "scoreText": "93.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 (xhigh)", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis GPQA Diamond leaderboard row for the xhigh reasoning variant." }, "gpqadiamond_accuracy_gpt55high_benchmarkleaderboard_247": { "label": "GPQA Diamond", "category": "science", "score": 93.2, "scoreText": "93.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 (high)", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis GPQA Diamond leaderboard row for the high reasoning variant." } } }, { "id": "azure/azure/gpt-5.5-2026-04-23", "slug": "azure-azure-gpt-5-5-2026-04-23", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.5-2026-04-23", "displayName": "gpt-5.5-2026-04-23", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 10, "priorityOutputUsdPer1MTokens": 60, "priorityCachedInputUsdPer1MTokens": 1, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 10, "above272kOutputUsdPer1MTokens": 45, "above272kCachedInputUsdPer1MTokens": 1, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "output_cost_per_token": 0.00003, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.5-2026-04-23", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00003, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true }, "benchmarks": { "livebench_livebenchscore_gpt55thinkingxhigheffort_benchmarkleaderboard_227": { "label": "LiveBench", "category": "general_knowledge", "score": 80.71, "scoreText": "80.71", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt55high_benchmarkleaderboard_242": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1487, "scoreText": "1487±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "gpt-5.5-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." }, "gpqadiamond_accuracy_gpt55xhigh_benchmarkleaderboard_246": { "label": "GPQA Diamond", "category": "science", "score": 93.5, "scoreText": "93.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 (xhigh)", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis GPQA Diamond leaderboard row for the xhigh reasoning variant." }, "gpqadiamond_accuracy_gpt55high_benchmarkleaderboard_247": { "label": "GPQA Diamond", "category": "science", "score": 93.2, "scoreText": "93.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 (high)", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis GPQA Diamond leaderboard row for the high reasoning variant." } } }, { "id": "azure/azure/gpt-5.5-pro", "slug": "azure-azure-gpt-5-5-pro", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.5-pro", "displayName": "gpt-5.5-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 180, "cachedInputUsdPer1MTokens": 3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 60, "above272kOutputUsdPer1MTokens": 270, "above272kCachedInputUsdPer1MTokens": 6, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false, "low_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.5-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure/azure/gpt-5.5-pro-2026-04-23", "slug": "azure-azure-gpt-5-5-pro-2026-04-23", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.5-pro-2026-04-23", "displayName": "gpt-5.5-pro-2026-04-23", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 180, "cachedInputUsdPer1MTokens": 3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 60, "above272kOutputUsdPer1MTokens": 270, "above272kCachedInputUsdPer1MTokens": 6, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.5-pro-2026-04-23", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure/azure/gpt-5.4-mini", "slug": "azure-azure-gpt-5-4-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.4-mini", "displayName": "gpt-5.4-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.75, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.4-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 7.5e-7, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000045, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false } }, { "id": "azure/azure/gpt-5.4-mini-2026-03-17", "slug": "azure-azure-gpt-5-4-mini-2026-03-17", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.4-mini-2026-03-17", "displayName": "gpt-5.4-mini-2026-03-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.75, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.4-mini-2026-03-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 7.5e-7, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000045, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false } }, { "id": "azure/azure/gpt-5.4-nano", "slug": "azure-azure-gpt-5-4-nano", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.4-nano", "displayName": "gpt-5.4-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-8, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.4-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2e-8, "input_cost_per_token": 2e-7, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000125, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false } }, { "id": "azure/azure/gpt-5.4-nano-2026-03-17", "slug": "azure-azure-gpt-5-4-nano-2026-03-17", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.4-nano-2026-03-17", "displayName": "gpt-5.4-nano-2026-03-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-8, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-5.4-nano-2026-03-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2e-8, "input_cost_per_token": 2e-7, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000125, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false } }, { "id": "azure/azure/gpt-image-1", "slug": "azure-azure-gpt-image-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1", "displayName": "gpt-image-1", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.0000025, "cache_read_input_token_cost": 0.00000125, "input_cost_per_image_token": 0.00001, "input_cost_per_token": 0.000005, "output_cost_per_image_token": 0.00004 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.0000025, "cache_read_input_token_cost": 0.00000125, "input_cost_per_image_token": 0.00001, "input_cost_per_token": 0.000005, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 0.00004, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "id": "azure/azure/hd/1024-x-1024/dall-e-3", "slug": "azure-azure-hd-1024-x-1024-dall-e-3", "provider": "Azure", "providerSlug": "azure", "name": "dall-e-3", "displayName": "dall-e-3 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 7.629e-8, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 7.629e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/hd/1024-x-1024/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 7.629e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0 } }, { "id": "azure/azure/hd/1024-x-1792/dall-e-3", "slug": "azure-azure-hd-1024-x-1792-dall-e-3", "provider": "Azure", "providerSlug": "azure", "name": "dall-e-3", "displayName": "dall-e-3 (1024x1792)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 6.539e-8, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 6.539e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/hd/1024-x-1792/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 6.539e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0 } }, { "id": "azure/azure/hd/1792-x-1024/dall-e-3", "slug": "azure-azure-hd-1792-x-1024-dall-e-3", "provider": "Azure", "providerSlug": "azure", "name": "dall-e-3", "displayName": "dall-e-3 (1792x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 6.539e-8, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 6.539e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/hd/1792-x-1024/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 6.539e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0 } }, { "id": "azure/azure/high/1024-x-1024/gpt-image-1", "slug": "azure-azure-high-1024-x-1024-gpt-image-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.59263611e-7, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 1.59263611e-7, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/high/1024-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 1.59263611e-7, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/high/1024-x-1536/gpt-image-1", "slug": "azure-azure-high-1024-x-1536-gpt-image-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.58945719e-7, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 1.58945719e-7, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/high/1024-x-1536/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 1.58945719e-7, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/high/1536-x-1024/gpt-image-1", "slug": "azure-azure-high-1536-x-1024-gpt-image-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1", "displayName": "gpt-image-1 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.58945719e-7, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 1.58945719e-7, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/high/1536-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 1.58945719e-7, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/low/1024-x-1024/gpt-image-1", "slug": "azure-azure-low-1024-x-1024-gpt-image-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.0490417e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 1.0490417e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/low/1024-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 1.0490417e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/low/1024-x-1536/gpt-image-1", "slug": "azure-azure-low-1024-x-1536-gpt-image-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.0172526e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 1.0172526e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/low/1024-x-1536/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 1.0172526e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/low/1536-x-1024/gpt-image-1", "slug": "azure-azure-low-1536-x-1024-gpt-image-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1", "displayName": "gpt-image-1 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.0172526e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 1.0172526e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/low/1536-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 1.0172526e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/medium/1024-x-1024/gpt-image-1", "slug": "azure-azure-medium-1024-x-1024-gpt-image-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 4.0054321e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 4.0054321e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/medium/1024-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 4.0054321e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/medium/1024-x-1536/gpt-image-1", "slug": "azure-azure-medium-1024-x-1536-gpt-image-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 4.0054321e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 4.0054321e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/medium/1024-x-1536/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 4.0054321e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/medium/1536-x-1024/gpt-image-1", "slug": "azure-azure-medium-1536-x-1024-gpt-image-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1", "displayName": "gpt-image-1 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 4.0054321e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 4.0054321e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/medium/1536-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 4.0054321e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/gpt-image-1-mini", "slug": "azure-azure-gpt-image-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 2.5e-7, "cache_read_input_token_cost": 2e-7, "input_cost_per_image_token": 0.0000025, "input_cost_per_token": 0.000002, "output_cost_per_image_token": 0.000008 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 2.5e-7, "cache_read_input_token_cost": 2e-7, "input_cost_per_image_token": 0.0000025, "input_cost_per_token": 0.000002, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 0.000008, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "id": "azure/azure/gpt-image-1.5", "slug": "azure-azure-gpt-image-1-5", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.000032 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 0.000032, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "id": "azure/azure/gpt-image-1.5-2025-12-16", "slug": "azure-azure-gpt-image-1-5-2025-12-16", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.000032 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 0.000032, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "id": "azure/azure/gpt-image-2", "slug": "azure-azure-gpt-image-2", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-2", "displayName": "gpt-image-2", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "output_cost_per_token": 0.00001, "output_cost_per_image_token": 0.00003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-image-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0.00001, "output_cost_per_image_token": 0.00003, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "azure/azure/gpt-image-2-2026-04-21", "slug": "azure-azure-gpt-image-2-2026-04-21", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-2-2026-04-21", "displayName": "gpt-image-2-2026-04-21", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "output_cost_per_token": 0.00001, "output_cost_per_image_token": 0.00003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/gpt-image-2-2026-04-21", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0.00001, "output_cost_per_image_token": 0.00003, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "azure/azure/low/1024-x-1024/gpt-image-1-mini", "slug": "azure-azure-low-1024-x-1024-gpt-image-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 2.0751953125e-9, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 2.0751953125e-9, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/low/1024-x-1024/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 2.0751953125e-9, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/low/1024-x-1536/gpt-image-1-mini", "slug": "azure-azure-low-1024-x-1536-gpt-image-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 2.0751953125e-9, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 2.0751953125e-9, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/low/1024-x-1536/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 2.0751953125e-9, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/low/1536-x-1024/gpt-image-1-mini", "slug": "azure-azure-low-1536-x-1024-gpt-image-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 2.0345052083e-9, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 2.0345052083e-9, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/low/1536-x-1024/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 2.0345052083e-9, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/medium/1024-x-1024/gpt-image-1-mini", "slug": "azure-azure-medium-1024-x-1024-gpt-image-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 8.056640625e-9, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 8.056640625e-9, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/medium/1024-x-1024/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 8.056640625e-9, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/medium/1024-x-1536/gpt-image-1-mini", "slug": "azure-azure-medium-1024-x-1536-gpt-image-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 8.056640625e-9, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 8.056640625e-9, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/medium/1024-x-1536/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 8.056640625e-9, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/medium/1536-x-1024/gpt-image-1-mini", "slug": "azure-azure-medium-1536-x-1024-gpt-image-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 7.9752604167e-9, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 7.9752604167e-9, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/medium/1536-x-1024/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 7.9752604167e-9, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/high/1024-x-1024/gpt-image-1-mini", "slug": "azure-azure-high-1024-x-1024-gpt-image-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 3.173828125e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 3.173828125e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/high/1024-x-1024/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 3.173828125e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/high/1024-x-1536/gpt-image-1-mini", "slug": "azure-azure-high-1024-x-1536-gpt-image-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 3.173828125e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 3.173828125e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/high/1024-x-1536/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 3.173828125e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/high/1536-x-1024/gpt-image-1-mini", "slug": "azure-azure-high-1536-x-1024-gpt-image-1-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 3.1575520833e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 3.1575520833e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/high/1536-x-1024/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 3.1575520833e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure/azure/mistral-large-2402", "slug": "azure-azure-mistral-large-2402", "provider": "Azure", "providerSlug": "azure", "name": "mistral-large-2402", "displayName": "mistral-large-2402", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": null, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/mistral-large-2402", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "azure", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000024, "supports_function_calling": true } }, { "id": "azure/azure/mistral-large-latest", "slug": "azure-azure-mistral-large-latest", "provider": "Azure", "providerSlug": "azure", "name": "mistral-large-latest", "displayName": "mistral-large-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": null, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/mistral-large-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "azure", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000024, "supports_function_calling": true } }, { "id": "azure/azure/o1", "slug": "azure-azure-o1", "provider": "Azure", "providerSlug": "azure", "name": "azure", "displayName": "azure", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": 7.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure o1 exact ids from official model tables" } }, { "id": "azure/azure/o1-2024-12-17", "slug": "azure-azure-o1-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "o1-2024-12-17", "displayName": "o1-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": 7.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o1-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure o1 exact ids from official model tables" } }, { "id": "azure/azure/o1-mini", "slug": "azure-azure-o1-mini", "provider": "Azure", "providerSlug": "azure", "name": "o1-mini", "displayName": "o1-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.21, "outputUsdPer1MTokens": 4.84, "cachedInputUsdPer1MTokens": 0.605, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 128000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "reasoning": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.00000484, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&view=rest-azureopenai-2024-08-01-preview", "https://platform.openai.com/docs/models/o1-mini" ], "manual_model_modalities_note": "Azure exact reasoning model id from official docs." } }, { "id": "azure/azure/o1-mini-2024-09-12", "slug": "azure-azure-o1-mini-2024-09-12", "provider": "Azure", "providerSlug": "azure", "name": "o1-mini-2024-09-12", "displayName": "o1-mini-2024-09-12", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 128000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "reasoning": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o1-mini-2024-09-12", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&view=rest-azureopenai-2024-08-01-preview", "https://platform.openai.com/docs/models/o1-mini" ], "manual_model_modalities_note": "Azure exact reasoning model id from official docs." } }, { "id": "azure/azure/o1-preview", "slug": "azure-azure-o1-preview", "provider": "Azure", "providerSlug": "azure", "name": "o1-preview", "displayName": "o1-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": 7.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 128000, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "reasoning": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o1-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&view=rest-azureopenai-2024-08-01-preview", "https://platform.openai.com/docs/models/o1-preview" ], "manual_model_modalities_note": "Azure exact reasoning model id from official docs." } }, { "id": "azure/azure/o1-preview-2024-09-12", "slug": "azure-azure-o1-preview-2024-09-12", "provider": "Azure", "providerSlug": "azure", "name": "o1-preview-2024-09-12", "displayName": "o1-preview-2024-09-12", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": 7.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 128000, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o1-preview-2024-09-12", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&view=rest-azureopenai-2024-08-01-preview", "https://platform.openai.com/docs/models/o1-preview" ], "manual_model_modalities_note": "Azure exact reasoning model id from official docs." } }, { "id": "azure/azure/o3", "slug": "azure-azure-o3", "provider": "Azure", "providerSlug": "azure", "name": "azure", "displayName": "azure", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o3", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000008, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "aime2025_accuracy_openaio3high_officiallaunchpost_12": { "label": "AIME 2025", "category": "reasoning", "score": 88.9, "scoreText": "88.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio3high_officiallaunchpost_13": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio3high_officiallaunchpost_14": { "label": "SWE-bench Verified", "category": "coding", "score": 69.1, "scoreText": "69.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "azure/azure/o3-2025-04-16", "slug": "azure-azure-o3-2025-04-16", "provider": "Azure", "providerSlug": "azure", "name": "o3-2025-04-16", "displayName": "o3-2025-04-16", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": "2026-04-16" }, "source": { "type": "litellm", "litellmKey": "azure/o3-2025-04-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-04-16", "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000008, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "aime2025_accuracy_openaio3high_officiallaunchpost_12": { "label": "AIME 2025", "category": "reasoning", "score": 88.9, "scoreText": "88.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio3high_officiallaunchpost_13": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio3high_officiallaunchpost_14": { "label": "SWE-bench Verified", "category": "coding", "score": 69.1, "scoreText": "69.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "azure/azure/o3-deep-research", "slug": "azure-azure-o3-deep-research", "provider": "Azure", "providerSlug": "azure", "name": "o3-deep-research", "displayName": "o3-deep-research", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 40, "cachedInputUsdPer1MTokens": 2.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00004 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o3-deep-research", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_token": 0.00001, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.00004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure/azure/o3-mini", "slug": "azure-azure-o3-mini", "provider": "Azure", "providerSlug": "azure", "name": "o3-mini", "displayName": "o3-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o3-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure o3-mini exact ids from official model tables" }, "benchmarks": { "aime2024_accuracy_o3minihigh_officiallaunchpost_18": { "label": "AIME 2024", "category": "reasoning", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "gpqadiamond_accuracy_o3minihigh_officiallaunchpost_19": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 77, "scoreText": "77.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "swebenchverified_accuracy_o3minihigh_officiallaunchpost_20": { "label": "SWE-bench Verified", "category": "coding", "score": 48.9, "scoreText": "48.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; n=477 verified tasks." } } }, { "id": "azure/azure/o3-mini-2025-01-31", "slug": "azure-azure-o3-mini-2025-01-31", "provider": "Azure", "providerSlug": "azure", "name": "o3-mini-2025-01-31", "displayName": "o3-mini-2025-01-31", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o3-mini-2025-01-31", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability" ], "manual_model_modalities_note": "Azure o3-mini exact ids from official model tables" }, "benchmarks": { "aime2024_accuracy_o3minihigh_officiallaunchpost_18": { "label": "AIME 2024", "category": "reasoning", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "gpqadiamond_accuracy_o3minihigh_officiallaunchpost_19": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 77, "scoreText": "77.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "swebenchverified_accuracy_o3minihigh_officiallaunchpost_20": { "label": "SWE-bench Verified", "category": "coding", "score": 48.9, "scoreText": "48.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; n=477 verified tasks." } } }, { "id": "azure/azure/o3-pro", "slug": "azure-azure-o3-pro", "provider": "Azure", "providerSlug": "azure", "name": "o3-pro", "displayName": "o3-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 20, "outputUsdPer1MTokens": 80, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 20, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 10, "batchOutputUsdPer1MTokens": 40, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00002, "input_cost_per_token_batches": 0.00001, "output_cost_per_token": 0.00008, "output_cost_per_token_batches": 0.00004 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": false, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o3-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00002, "input_cost_per_token_batches": 0.00001, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.00008, "output_cost_per_token_batches": 0.00004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "gpqadiamond_accuracy_openaio3pro_benchmarkleaderboard_262": { "label": "GPQA Diamond", "category": "reasoning", "score": 84.5, "scoreText": "84.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/o3-pro/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "o3 Pro", "exactModelOrSnapshot": "openai/o3-pro", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. The page cites Artificial Analysis for the metric source." } } }, { "id": "azure/azure/o3-pro-2025-06-10", "slug": "azure-azure-o3-pro-2025-06-10", "provider": "Azure", "providerSlug": "azure", "name": "o3-pro-2025-06-10", "displayName": "o3-pro-2025-06-10", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 20, "outputUsdPer1MTokens": 80, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 20, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 10, "batchOutputUsdPer1MTokens": 40, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00002, "input_cost_per_token_batches": 0.00001, "output_cost_per_token": 0.00008, "output_cost_per_token_batches": 0.00004 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": false, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o3-pro-2025-06-10", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00002, "input_cost_per_token_batches": 0.00001, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.00008, "output_cost_per_token_batches": 0.00004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "gpqadiamond_accuracy_openaio3pro_benchmarkleaderboard_262": { "label": "GPQA Diamond", "category": "reasoning", "score": 84.5, "scoreText": "84.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/o3-pro/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "o3 Pro", "exactModelOrSnapshot": "openai/o3-pro", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. The page cites Artificial Analysis for the metric source." } } }, { "id": "azure/azure/o4-mini", "slug": "azure-azure-o4-mini", "provider": "Azure", "providerSlug": "azure", "name": "o4-mini", "displayName": "o4-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.275, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.75e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o4-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.75e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "aime2025_accuracy_openaio4minihigh_officiallaunchpost_15": { "label": "AIME 2025", "category": "reasoning", "score": 92.7, "scoreText": "92.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio4minihigh_officiallaunchpost_16": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 81.4, "scoreText": "81.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio4minihigh_officiallaunchpost_17": { "label": "SWE-bench Verified", "category": "coding", "score": 68.1, "scoreText": "68.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "azure/azure/o4-mini-2025-04-16", "slug": "azure-azure-o4-mini-2025-04-16", "provider": "Azure", "providerSlug": "azure", "name": "o4-mini-2025-04-16", "displayName": "o4-mini-2025-04-16", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.275, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.75e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/o4-mini-2025-04-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.75e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?portal=true", "https://platform.openai.com/docs/models/o4-mini" ], "manual_model_modalities_note": "Azure exact reasoning model id from official docs." }, "benchmarks": { "aime2025_accuracy_openaio4minihigh_officiallaunchpost_15": { "label": "AIME 2025", "category": "reasoning", "score": 92.7, "scoreText": "92.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio4minihigh_officiallaunchpost_16": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 81.4, "scoreText": "81.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio4minihigh_officiallaunchpost_17": { "label": "SWE-bench Verified", "category": "coding", "score": 68.1, "scoreText": "68.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "azure/azure/standard/1024-x-1024/dall-e-2", "slug": "azure-azure-standard-1024-x-1024-dall-e-2", "provider": "Azure", "providerSlug": "azure", "name": "dall-e-2", "displayName": "dall-e-2 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 0, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/standard/1024-x-1024/dall-e-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 0, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0 } }, { "id": "azure/azure/standard/1024-x-1024/dall-e-3", "slug": "azure-azure-standard-1024-x-1024-dall-e-3", "provider": "Azure", "providerSlug": "azure", "name": "dall-e-3", "displayName": "dall-e-3 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 3.81469e-8, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 3.81469e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/standard/1024-x-1024/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 3.81469e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0 } }, { "id": "azure/azure/standard/1024-x-1792/dall-e-3", "slug": "azure-azure-standard-1024-x-1792-dall-e-3", "provider": "Azure", "providerSlug": "azure", "name": "dall-e-3", "displayName": "dall-e-3 (1024x1792)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 4.359e-8, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 4.359e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/standard/1024-x-1792/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 4.359e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0 } }, { "id": "azure/azure/standard/1792-x-1024/dall-e-3", "slug": "azure-azure-standard-1792-x-1024-dall-e-3", "provider": "Azure", "providerSlug": "azure", "name": "dall-e-3", "displayName": "dall-e-3 (1792x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 4.359e-8, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 4.359e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/standard/1792-x-1024/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 4.359e-8, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0 } }, { "id": "azure/azure/text-embedding-3-large", "slug": "azure-azure-text-embedding-3-large", "provider": "Azure", "providerSlug": "azure", "name": "text-embedding-3-large", "displayName": "text-embedding-3-large", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/text-embedding-3-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.3e-7, "litellm_provider": "azure", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "azure/azure/text-embedding-3-small", "slug": "azure-azure-text-embedding-3-small", "provider": "Azure", "providerSlug": "azure", "name": "text-embedding-3-small", "displayName": "text-embedding-3-small", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-04-30" }, "source": { "type": "litellm", "litellmKey": "azure/text-embedding-3-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-04-30", "input_cost_per_token": 2e-8, "litellm_provider": "azure", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "azure/azure/text-embedding-ada-002", "slug": "azure-azure-text-embedding-ada-002", "provider": "Azure", "providerSlug": "azure", "name": "text-embedding-ada-002", "displayName": "text-embedding-ada-002", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/text-embedding-ada-002", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "azure", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "azure/azure/speech/azure-tts", "slug": "azure-azure-speech-azure-tts", "provider": "Azure", "providerSlug": "azure", "name": "azure-tts", "displayName": "azure-tts", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.000015, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.000015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/speech/azure-tts", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/calculator/" }, "rawLitellm": { "input_cost_per_character": 0.000015, "litellm_provider": "azure", "mode": "audio_speech", "source": "https://azure.microsoft.com/en-us/pricing/calculator/" } }, { "id": "azure/azure/speech/azure-tts-hd", "slug": "azure-azure-speech-azure-tts-hd", "provider": "Azure", "providerSlug": "azure", "name": "azure-tts-hd", "displayName": "azure-tts-hd", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00003, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/speech/azure-tts-hd", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/calculator/" }, "rawLitellm": { "input_cost_per_character": 0.00003, "litellm_provider": "azure", "mode": "audio_speech", "source": "https://azure.microsoft.com/en-us/pricing/calculator/" } }, { "id": "azure/azure/tts-1", "slug": "azure-azure-tts-1", "provider": "Azure", "providerSlug": "azure", "name": "tts-1", "displayName": "tts-1", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.000015, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.000015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/tts-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.000015, "litellm_provider": "azure", "mode": "audio_speech" } }, { "id": "azure/azure/tts-1-hd", "slug": "azure-azure-tts-1-hd", "provider": "Azure", "providerSlug": "azure", "name": "tts-1-hd", "displayName": "tts-1-hd", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00003, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/tts-1-hd", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.00003, "litellm_provider": "azure", "mode": "audio_speech" } }, { "id": "azure/azure/us/gpt-4.1-2025-04-14", "slug": "azure-azure-us-gpt-4-1-2025-04-14", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4.1-2025-04-14", "displayName": "gpt-4.1-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.2, "outputUsdPer1MTokens": 8.8, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.1, "batchOutputUsdPer1MTokens": 4.4, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000022, "input_cost_per_token_batches": 0.0000011, "output_cost_per_token": 0.0000088, "output_cost_per_token_batches": 0.0000044 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": false } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": "2026-11-04" }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-4.1-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000022, "input_cost_per_token_batches": 0.0000011, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000088, "output_cost_per_token_batches": 0.0000044, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "azure/azure/us/gpt-4.1-mini-2025-04-14", "slug": "azure-azure-us-gpt-4-1-mini-2025-04-14", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4.1-mini-2025-04-14", "displayName": "gpt-4.1-mini-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.44, "outputUsdPer1MTokens": 1.76, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.44, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.22, "batchOutputUsdPer1MTokens": 0.88, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 4.4e-7, "input_cost_per_token_batches": 2.2e-7, "output_cost_per_token": 0.00000176, "output_cost_per_token_batches": 8.8e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": false } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": "2026-11-04" }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-4.1-mini-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 4.4e-7, "input_cost_per_token_batches": 2.2e-7, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.00000176, "output_cost_per_token_batches": 8.8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false }, "benchmarks": { "swebenchverified_accuracy_gpt41mini_officiallaunchpost_5": { "label": "SWE-bench Verified", "category": "coding", "score": 23.6, "scoreText": "23.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-mini", "exactModelOrSnapshot": "GPT-4.1 mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table for the GPT-4.1 family." } } }, { "id": "azure/azure/us/gpt-4.1-nano-2025-04-14", "slug": "azure-azure-us-gpt-4-1-nano-2025-04-14", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4.1-nano-2025-04-14", "displayName": "gpt-4.1-nano-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.11, "outputUsdPer1MTokens": 0.44, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.11, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.06, "batchOutputUsdPer1MTokens": 0.22, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1.1e-7, "input_cost_per_token_batches": 6e-8, "output_cost_per_token": 4.4e-7, "output_cost_per_token_batches": 2.2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": "2026-11-04" }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-4.1-nano-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1.1e-7, "input_cost_per_token_batches": 6e-8, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4.4e-7, "output_cost_per_token_batches": 2.2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "aime24_accuracy_gpt41nano_officiallaunchpost_6": { "label": "AIME 2024", "category": "reasoning", "score": 29.4, "scoreText": "29.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-nano", "exactModelOrSnapshot": "GPT-4.1 nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Academic-knowledge appendix comparison row for the nano model." }, "mmlu_accuracy_gpt41nano_officiallaunchpost_258": { "label": "MMLU", "category": "general_knowledge", "score": 80.1, "scoreText": "80.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the narrative and table." }, "gpqa_accuracy_gpt41nano_officiallaunchpost_259": { "label": "GPQA", "category": "reasoning", "score": 50.3, "scoreText": "50.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." }, "aiderpolyglotcoding_passrate_gpt41nano_officiallaunchpost_260": { "label": "Aider Polyglot", "category": "coding", "score": 9.8, "scoreText": "9.8%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." } } }, { "id": "azure/azure/us/gpt-4o-2024-08-06", "slug": "azure-azure-us-gpt-4o-2024-08-06", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-08-06", "displayName": "gpt-4o-2024-08-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.75, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 1.375, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000001375, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-02-27" }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-4o-2024-08-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-02-27", "cache_read_input_token_cost": 0.000001375, "input_cost_per_token": 0.00000275, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000011, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=global-standard%2Cstandard-image-generations" ], "manual_model_modalities_note": "Azure exact US model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/us/gpt-4o-2024-11-20", "slug": "azure-azure-us-gpt-4o-2024-11-20", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-2024-11-20", "displayName": "gpt-4o-2024-11-20", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.75, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": 1.38, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000138, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-03-01" }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-4o-2024-11-20", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-03-01", "cache_creation_input_token_cost": 0.00000138, "input_cost_per_token": 0.00000275, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000011, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=global-standard%2Cstandard-image-generations" ], "manual_model_modalities_note": "Azure exact US model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/us/gpt-4o-mini-2024-07-18", "slug": "azure-azure-us-gpt-4o-mini-2024-07-18", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini-2024-07-18", "displayName": "gpt-4o-mini-2024-07-18", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.165, "outputUsdPer1MTokens": 0.66, "cachedInputUsdPer1MTokens": 0.083, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.165, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 8.3e-8, "input_cost_per_token": 1.65e-7, "output_cost_per_token": 6.6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-4o-mini-2024-07-18", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 8.3e-8, "input_cost_per_token": 1.65e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=global-standard%2Cstandard-image-generations" ], "manual_model_modalities_note": "Azure exact US model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/us/gpt-4o-mini-realtime-preview-2024-12-17", "slug": "azure-azure-us-gpt-4o-mini-realtime-preview-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-mini-realtime-preview-2024-12-17", "displayName": "gpt-4o-mini-realtime-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.66, "outputUsdPer1MTokens": 2.64, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 11, "audioOutputUsdPer1MTokens": 22, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.66, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 3.3e-7, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_audio_token": 0.000011, "input_cost_per_token": 6.6e-7, "output_cost_per_audio_token": 0.000022, "output_cost_per_token": 0.00000264 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "audio", "image" ], "input": [ "audio", "image" ], "output": [ "audio" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-4o-mini-realtime-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 3.3e-7, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_audio_token": 0.000011, "input_cost_per_token": 6.6e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.000022, "output_cost_per_token": 0.00000264, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio" ], "manual_model_modalities_note": "Azure exact US realtime model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "azure/azure/us/gpt-4o-realtime-preview-2024-10-01", "slug": "azure-azure-us-gpt-4o-realtime-preview-2024-10-01", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-realtime-preview-2024-10-01", "displayName": "gpt-4o-realtime-preview-2024-10-01", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 22, "cachedInputUsdPer1MTokens": 2.75, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 110, "audioOutputUsdPer1MTokens": 220, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 0.000022, "cache_read_input_token_cost": 0.00000275, "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 0.0000055, "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 0.000022 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "audio", "image", "text" ], "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-4o-realtime-preview-2024-10-01", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 0.000022, "cache_read_input_token_cost": 0.00000275, "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 0.0000055, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 0.000022, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio?tabs=keyless%2Cwindows" ], "manual_model_modalities_note": "Azure exact US realtime model id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/us/gpt-4o-realtime-preview-2024-12-17", "slug": "azure-azure-us-gpt-4o-realtime-preview-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "gpt-4o-realtime-preview-2024-12-17", "displayName": "gpt-4o-realtime-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 22, "cachedInputUsdPer1MTokens": 2.75, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 44, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_audio_token_cost": 0.0000025, "cache_read_input_token_cost": 0.00000275, "input_cost_per_audio_token": 0.000044, "input_cost_per_token": 0.0000055, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.000022 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-4o-realtime-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_audio_token_cost": 0.0000025, "cache_read_input_token_cost": 0.00000275, "input_cost_per_audio_token": 0.000044, "input_cost_per_token": 0.0000055, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.000022, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "azure/azure/us/gpt-5-2025-08-07", "slug": "azure-azure-us-gpt-5-2025-08-07", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-2025-08-07", "displayName": "gpt-5-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.375, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 0.1375, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.375, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.375e-7, "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-5-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.375e-7, "input_cost_per_token": 0.000001375, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000011, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "azure/azure/us/gpt-5-mini-2025-08-07", "slug": "azure-azure-us-gpt-5-mini-2025-08-07", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-mini-2025-08-07", "displayName": "gpt-5-mini-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.275, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.0275, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.275, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.75e-8, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-5-mini-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.75e-8, "input_cost_per_token": 2.75e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000022, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "azure/azure/us/gpt-5-nano-2025-08-07", "slug": "azure-azure-us-gpt-5-nano-2025-08-07", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5-nano-2025-08-07", "displayName": "gpt-5-nano-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.055, "outputUsdPer1MTokens": 0.44, "cachedInputUsdPer1MTokens": 0.0055, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.055, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.5e-9, "input_cost_per_token": 5.5e-8, "output_cost_per_token": 4.4e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-5-nano-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.5e-9, "input_cost_per_token": 5.5e-8, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "aime2025_accuracy_gpt5nanohigh_officiallaunchpost_28": { "label": "AIME 2025", "category": "reasoning", "score": 85.2, "scoreText": "85.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-nano", "exactModelOrSnapshot": "GPT-5 nano (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." } } }, { "id": "azure/azure/us/gpt-5.1", "slug": "azure-azure-us-gpt-5-1", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1", "displayName": "gpt-5.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.38, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 0.14, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "none_reasoning_effort": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-5.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000011, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/us/gpt-5.1-chat", "slug": "azure-azure-us-gpt-5-1-chat", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-chat", "displayName": "gpt-5.1-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.38, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 0.14, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "none_reasoning_effort": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-5.1-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000011, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/us/gpt-5.1-codex", "slug": "azure-azure-us-gpt-5-1-codex", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex", "displayName": "gpt-5.1-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.38, "outputUsdPer1MTokens": 11, "cachedInputUsdPer1MTokens": 0.14, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-5.1-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.00000138, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000011, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/us/gpt-5.1-codex-mini", "slug": "azure-azure-us-gpt-5-1-codex-mini", "provider": "Azure", "providerSlug": "azure", "name": "gpt-5.1-codex-mini", "displayName": "gpt-5.1-codex-mini", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 0.275, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.028, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.275, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/gpt-5.1-codex-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.75e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.0000022, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "azure/azure/us/o1-2024-12-17", "slug": "azure-azure-us-o1-2024-12-17", "provider": "Azure", "providerSlug": "azure", "name": "o1-2024-12-17", "displayName": "o1-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 16.5, "outputUsdPer1MTokens": 66, "cachedInputUsdPer1MTokens": 8.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 16.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000825, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.000066 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/o1-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000825, "input_cost_per_token": 0.0000165, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000066, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?tabs=global-standard%2Cstandard-image-generations", "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reasoning" ], "manual_model_modalities_note": "Azure exact US reasoning model id from official docs." } }, { "id": "azure/azure/us/o1-mini-2024-09-12", "slug": "azure-azure-us-o1-mini-2024-09-12", "provider": "Azure", "providerSlug": "azure", "name": "o1-mini-2024-09-12", "displayName": "o1-mini-2024-09-12", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.21, "outputUsdPer1MTokens": 4.84, "cachedInputUsdPer1MTokens": 0.605, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.605, "batchOutputUsdPer1MTokens": 2.42, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "input_cost_per_token_batches": 6.05e-7, "output_cost_per_token": 0.00000484, "output_cost_per_token_batches": 0.00000242 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 128000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/o1-mini-2024-09-12", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "input_cost_per_token_batches": 6.05e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.00000484, "output_cost_per_token_batches": 0.00000242, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&view=rest-azureopenai-2024-08-01-preview", "https://platform.openai.com/docs/models/o1-mini" ], "manual_model_modalities_note": "Azure exact US reasoning model id from official docs." } }, { "id": "azure/azure/us/o1-preview-2024-09-12", "slug": "azure-azure-us-o1-preview-2024-09-12", "provider": "Azure", "providerSlug": "azure", "name": "o1-preview-2024-09-12", "displayName": "o1-preview-2024-09-12", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 16.5, "outputUsdPer1MTokens": 66, "cachedInputUsdPer1MTokens": 8.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 16.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000825, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.000066 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 128000, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/o1-preview-2024-09-12", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000825, "input_cost_per_token": 0.0000165, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000066, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?branch=main&tabs=python-secure", "https://developers.openai.com/api/docs/models/o1-preview" ], "manual_model_modalities_note": "Azure exact US reasoning model id from official docs." } }, { "id": "azure/azure/us/o3-2025-04-16", "slug": "azure-azure-us-o3-2025-04-16", "provider": "Azure", "providerSlug": "azure", "name": "o3-2025-04-16", "displayName": "o3-2025-04-16", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.2, "outputUsdPer1MTokens": 8.8, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000088 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": "2026-04-16" }, "source": { "type": "litellm", "litellmKey": "azure/us/o3-2025-04-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-04-16", "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000022, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000088, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "aime2025_accuracy_openaio3high_officiallaunchpost_12": { "label": "AIME 2025", "category": "reasoning", "score": 88.9, "scoreText": "88.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio3high_officiallaunchpost_13": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio3high_officiallaunchpost_14": { "label": "SWE-bench Verified", "category": "coding", "score": 69.1, "scoreText": "69.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "azure/azure/us/o3-mini-2025-01-31", "slug": "azure-azure-us-o3-mini-2025-01-31", "provider": "Azure", "providerSlug": "azure", "name": "o3-mini-2025-01-31", "displayName": "o3-mini-2025-01-31", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.21, "outputUsdPer1MTokens": 4.84, "cachedInputUsdPer1MTokens": 0.605, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.605, "batchOutputUsdPer1MTokens": 2.42, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "input_cost_per_token_batches": 6.05e-7, "output_cost_per_token": 0.00000484, "output_cost_per_token_batches": 0.00000242 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/o3-mini-2025-01-31", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "input_cost_per_token_batches": 6.05e-7, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00000484, "output_cost_per_token_batches": 0.00000242, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?branch=main&tabs=python-secure", "https://developers.openai.com/api/docs/models/o3-mini" ], "manual_model_modalities_note": "Azure exact US reasoning model id from official docs." }, "benchmarks": { "aime2024_accuracy_o3minihigh_officiallaunchpost_18": { "label": "AIME 2024", "category": "reasoning", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "gpqadiamond_accuracy_o3minihigh_officiallaunchpost_19": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 77, "scoreText": "77.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "swebenchverified_accuracy_o3minihigh_officiallaunchpost_20": { "label": "SWE-bench Verified", "category": "coding", "score": 48.9, "scoreText": "48.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; n=477 verified tasks." } } }, { "id": "azure/azure/us/o4-mini-2025-04-16", "slug": "azure-azure-us-o4-mini-2025-04-16", "provider": "Azure", "providerSlug": "azure", "name": "o4-mini-2025-04-16", "displayName": "o4-mini-2025-04-16", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.21, "outputUsdPer1MTokens": 4.84, "cachedInputUsdPer1MTokens": 0.31, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3.1e-7, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/us/o4-mini-2025-04-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 3.1e-7, "input_cost_per_token": 0.00000121, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00000484, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?branch=main&tabs=python-secure", "https://developers.openai.com/api/docs/models/o4-mini" ], "manual_model_modalities_note": "Azure exact US reasoning model id from official docs." }, "benchmarks": { "aime2025_accuracy_openaio4minihigh_officiallaunchpost_15": { "label": "AIME 2025", "category": "reasoning", "score": 92.7, "scoreText": "92.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio4minihigh_officiallaunchpost_16": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 81.4, "scoreText": "81.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio4minihigh_officiallaunchpost_17": { "label": "SWE-bench Verified", "category": "coding", "score": 68.1, "scoreText": "68.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "azure/azure/whisper-1", "slug": "azure-azure-whisper-1", "provider": "Azure", "providerSlug": "azure", "name": "whisper-1", "displayName": "whisper-1", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0001, "perSecondOutputUsd": 0.0001, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/whisper-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0001, "litellm_provider": "azure", "mode": "audio_transcription", "output_cost_per_second": 0.0001, "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/Cohere-embed-v3-english", "slug": "azure_ai-azure_ai-cohere-embed-v3-english", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Cohere-embed-v3-english", "displayName": "Cohere-embed-v3-english", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Cohere-embed-v3-english", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "azure_ai", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true } }, { "id": "azure_ai/azure_ai/Cohere-embed-v3-multilingual", "slug": "azure_ai-azure_ai-cohere-embed-v3-multilingual", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Cohere-embed-v3-multilingual", "displayName": "Cohere-embed-v3-multilingual", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Cohere-embed-v3-multilingual", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "azure_ai", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true } }, { "id": "azure_ai/azure_ai/FLUX-1.1-pro", "slug": "azure_ai-azure_ai-flux-1-1-pro", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "FLUX-1.1-pro", "displayName": "FLUX-1.1-pro", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/FLUX-1.1-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659" }, "rawLitellm": { "litellm_provider": "azure_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure_ai/azure_ai/FLUX.1-Kontext-pro", "slug": "azure_ai-azure_ai-flux-1-kontext-pro", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "FLUX.1-Kontext-pro", "displayName": "FLUX.1-Kontext-pro", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/FLUX.1-Kontext-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice" }, "rawLitellm": { "litellm_provider": "azure_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure_ai/azure_ai/flux.2-pro", "slug": "azure_ai-azure_ai-flux-2-pro", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "flux.2-pro", "displayName": "flux.2-pro", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/flux.2-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs" }, "rawLitellm": { "litellm_provider": "azure_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "azure_ai/azure_ai/Llama-3.2-11B-Vision-Instruct", "slug": "azure_ai-azure_ai-llama-3-2-11b-vision-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Llama-3.2-11B-Vision-Instruct", "displayName": "Llama-3.2-11B-Vision-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.37, "outputUsdPer1MTokens": 0.37, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.37, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.7e-7, "output_cost_per_token": 3.7e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Llama-3.2-11B-Vision-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview" }, "rawLitellm": { "input_cost_per_token": 3.7e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.7e-7, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-from-partners" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "azure_ai/azure_ai/Llama-3.2-90B-Vision-Instruct", "slug": "azure_ai-azure_ai-llama-3-2-90b-vision-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Llama-3.2-90B-Vision-Instruct", "displayName": "Llama-3.2-90B-Vision-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.04, "outputUsdPer1MTokens": 2.04, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000204, "output_cost_per_token": 0.00000204 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Llama-3.2-90B-Vision-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview" }, "rawLitellm": { "input_cost_per_token": 0.00000204, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.00000204, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-from-partners" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "azure_ai/azure_ai/Llama-3.3-70B-Instruct", "slug": "azure_ai-azure_ai-llama-3-3-70b-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.71, "outputUsdPer1MTokens": 0.71, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.71, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.1e-7, "output_cost_per_token": 7.1e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Llama-3.3-70B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview" }, "rawLitellm": { "input_cost_per_token": 7.1e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 7.1e-7, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "azure_ai/azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8", "slug": "azure_ai-azure_ai-llama-4-maverick-17b-128e-instruct-fp8", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Llama-4-Maverick-17B-128E-Instruct-FP8", "displayName": "Llama-4-Maverick-17B-128E-Instruct-FP8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.4100000000000001, "outputUsdPer1MTokens": 0.35, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.4100000000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000141, "output_cost_per_token": 3.5e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 1000000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/" }, "rawLitellm": { "input_cost_per_token": 0.00000141, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.5e-7, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://ai.meta.com/blog/llama-4-multimodal-intelligence/" ], "manual_model_modalities_note": "Azure AI exact route id from official docs" }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "azure_ai/azure_ai/Llama-4-Scout-17B-16E-Instruct", "slug": "azure_ai-azure_ai-llama-4-scout-17b-16e-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Llama-4-Scout-17B-16E-Instruct", "displayName": "Llama-4-Scout-17B-16E-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.78, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 7.8e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 10000000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Llama-4-Scout-17B-16E-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "azure_ai", "max_input_tokens": 10000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.8e-7, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners", "https://ai.meta.com/blog/llama-4-multimodal-intelligence/" ], "manual_model_modalities_note": "Azure AI exact route id from official docs" }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "azure_ai/azure_ai/Meta-Llama-3-70B-Instruct", "slug": "azure_ai-azure_ai-meta-llama-3-70b-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Meta-Llama-3-70B-Instruct", "displayName": "Meta-Llama-3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 0.37, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000011, "output_cost_per_token": 3.7e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 8192, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Meta-Llama-3-70B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000011, "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.7e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/Meta-Llama-3-70B-Instruct", "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/Meta-Llama-3.1-405B-Instruct", "slug": "azure_ai-azure_ai-meta-llama-3-1-405b-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Meta-Llama-3.1-405B-Instruct", "displayName": "Meta-Llama-3.1-405B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.33, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.33, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000533, "output_cost_per_token": 0.000016 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Meta-Llama-3.1-405B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice" }, "rawLitellm": { "input_cost_per_token": 0.00000533, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.000016, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/Meta-Llama-3.1-405B-Instruct", "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "azure_ai/azure_ai/Meta-Llama-3.1-70B-Instruct", "slug": "azure_ai-azure_ai-meta-llama-3-1-70b-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Meta-Llama-3.1-70B-Instruct", "displayName": "Meta-Llama-3.1-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.68, "outputUsdPer1MTokens": 3.54, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.68, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000268, "output_cost_per_token": 0.00000354 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Meta-Llama-3.1-70B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice" }, "rawLitellm": { "input_cost_per_token": 0.00000268, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.00000354, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/Meta-Llama-3.1-70B-Instruct", "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "azure_ai/azure_ai/Meta-Llama-3.1-8B-Instruct", "slug": "azure_ai-azure_ai-meta-llama-3-1-8b-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Meta-Llama-3.1-8B-Instruct", "displayName": "Meta-Llama-3.1-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.61, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 6.1e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Meta-Llama-3.1-8B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 6.1e-7, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/Meta-Llama-3.1-8B-Instruct", "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "azure_ai/azure_ai/Phi-3-medium-128k-instruct", "slug": "azure_ai-azure_ai-phi-3-medium-128k-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-3-medium-128k-instruct", "displayName": "Phi-3-medium-128k-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.16999999999999998, "outputUsdPer1MTokens": 0.6799999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.16999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.7e-7, "output_cost_per_token": 6.8e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-3-medium-128k-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" }, "rawLitellm": { "input_cost_per_token": 1.7e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/Phi-3-medium-128k-instruct", "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." } } }, { "id": "azure_ai/azure_ai/Phi-3-medium-4k-instruct", "slug": "azure_ai-azure_ai-phi-3-medium-4k-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-3-medium-4k-instruct", "displayName": "Phi-3-medium-4k-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.16999999999999998, "outputUsdPer1MTokens": 0.6799999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.16999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.7e-7, "output_cost_per_token": 6.8e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-3-medium-4k-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" }, "rawLitellm": { "input_cost_per_token": 1.7e-7, "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.azure.com/catalog/models/Phi-3-medium-4k-instruct", "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." } } }, { "id": "azure_ai/azure_ai/Phi-3-mini-128k-instruct", "slug": "azure_ai-azure_ai-phi-3-mini-128k-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-3-mini-128k-instruct", "displayName": "Phi-3-mini-128k-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.52, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 5.2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-3-mini-128k-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" }, "rawLitellm": { "input_cost_per_token": 1.3e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2#microsoft" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." } } }, { "id": "azure_ai/azure_ai/Phi-3-mini-4k-instruct", "slug": "azure_ai-azure_ai-phi-3-mini-4k-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-3-mini-4k-instruct", "displayName": "Phi-3-mini-4k-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.52, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 5.2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-3-mini-4k-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" }, "rawLitellm": { "input_cost_per_token": 1.3e-7, "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2#microsoft" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." } } }, { "id": "azure_ai/azure_ai/Phi-3-small-128k-instruct", "slug": "azure_ai-azure_ai-phi-3-small-128k-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-3-small-128k-instruct", "displayName": "Phi-3-small-128k-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-3-small-128k-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2#microsoft" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." } } }, { "id": "azure_ai/azure_ai/Phi-3-small-8k-instruct", "slug": "azure_ai-azure_ai-phi-3-small-8k-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-3-small-8k-instruct", "displayName": "Phi-3-small-8k-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-3-small-8k-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2#microsoft" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." } } }, { "id": "azure_ai/azure_ai/Phi-3.5-MoE-instruct", "slug": "azure_ai-azure_ai-phi-3-5-moe-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-3.5-MoE-instruct", "displayName": "Phi-3.5-MoE-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.16, "outputUsdPer1MTokens": 0.64, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.16, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.6e-7, "output_cost_per_token": 6.4e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-3.5-MoE-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" }, "rawLitellm": { "input_cost_per_token": 1.6e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2#microsoft" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." } } }, { "id": "azure_ai/azure_ai/Phi-3.5-mini-instruct", "slug": "azure_ai-azure_ai-phi-3-5-mini-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-3.5-mini-instruct", "displayName": "Phi-3.5-mini-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.52, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 5.2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-3.5-mini-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" }, "rawLitellm": { "input_cost_per_token": 1.3e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2#microsoft", "https://learn.microsoft.com/en-us/rest/api/aifoundry/model-inference/get-model-info/get-model-info?view=rest-aifoundry-model-inference-2024-05-01-preview" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." } } }, { "id": "azure_ai/azure_ai/Phi-3.5-vision-instruct", "slug": "azure_ai-azure_ai-phi-3-5-vision-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-3.5-vision-instruct", "displayName": "Phi-3.5-vision-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.52, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 5.2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-3.5-vision-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/phi-3/" }, "rawLitellm": { "input_cost_per_token": 1.3e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mmmuval_score_phi35visioninstruct_officialmodelcard_388": { "label": "MMMU", "category": "multimodal", "score": 43, "scoreText": "43.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3.5-vision-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3.5 Vision", "exactModelOrSnapshot": "Phi-3.5-vision-instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the Phi-3.5 vision card." }, "local_mmbenchdeven_score_phi35visioninstruct_officialmodelcard_389": { "label": "MMBench", "category": "multimodal", "score": 81.9, "scoreText": "81.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3.5-vision-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3.5 Vision", "exactModelOrSnapshot": "Phi-3.5-vision-instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the Phi-3.5 vision card." }, "local_scienceqaimgtest_score_phi35visioninstruct_officialmodelcard_390": { "label": "ScienceQA (img-test)", "category": "multimodal", "score": 91.3, "scoreText": "91.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3.5-vision-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3.5 Vision", "exactModelOrSnapshot": "Phi-3.5-vision-instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the Phi-3.5 vision card." }, "local_mathvistatestmini_score_phi35visioninstruct_officialmodelcard_391": { "label": "MathVista", "category": "multimodal", "score": 43.9, "scoreText": "43.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3.5-vision-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3.5 Vision", "exactModelOrSnapshot": "Phi-3.5-vision-instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the Phi-3.5 vision card." }, "local_chartqatest_score_phi35visioninstruct_officialmodelcard_392": { "label": "ChartQA", "category": "multimodal", "score": 81.8, "scoreText": "81.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3.5-vision-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3.5 Vision", "exactModelOrSnapshot": "Phi-3.5-vision-instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the Phi-3.5 vision card." }, "local_textvqaval_score_phi35visioninstruct_officialmodelcard_393": { "label": "TextVQA", "category": "multimodal", "score": 72, "scoreText": "72.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3.5-vision-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3.5 Vision", "exactModelOrSnapshot": "Phi-3.5-vision-instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the Phi-3.5 vision card." } } }, { "id": "azure_ai/azure_ai/Phi-4", "slug": "azure_ai-azure_ai-phi-4", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-4", "displayName": "Phi-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.125, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.125, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.25e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-4", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495" }, "rawLitellm": { "input_cost_per_token": 1.25e-7, "litellm_provider": "azure_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-7, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/model-inference/concepts/models?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs" }, "benchmarks": { "mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_202": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "gpqa_science_phi414b_officialmodelcard_203": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "humaneval_codegeneration_phi414b_officialmodelcard_204": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "drop_reasoning_phi414b_officialmodelcard_205": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "local_mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_160": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_gpqa_science_phi414b_officialmodelcard_161": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_humaneval_codegeneration_phi414b_officialmodelcard_162": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_simpleqa_factualknowledge_phi414b_officialmodelcard_163": { "label": "SimpleQA", "category": "general_knowledge", "score": 3, "scoreText": "3.0", "metric": "Factual Knowledge", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_drop_reasoning_phi414b_officialmodelcard_164": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." } } }, { "id": "azure_ai/azure_ai/Phi-4-mini-instruct", "slug": "azure_ai-azure_ai-phi-4-mini-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-4-mini-instruct", "displayName": "Phi-4-mini-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 131072, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-4-mini-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112" }, "rawLitellm": { "input_cost_per_token": 7.5e-8, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/model-inference/concepts/models?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs" }, "benchmarks": { "mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_202": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "gpqa_science_phi414b_officialmodelcard_203": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "humaneval_codegeneration_phi414b_officialmodelcard_204": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "drop_reasoning_phi414b_officialmodelcard_205": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "local_mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_160": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_gpqa_science_phi414b_officialmodelcard_161": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_humaneval_codegeneration_phi414b_officialmodelcard_162": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_simpleqa_factualknowledge_phi414b_officialmodelcard_163": { "label": "SimpleQA", "category": "general_knowledge", "score": 3, "scoreText": "3.0", "metric": "Factual Knowledge", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_drop_reasoning_phi414b_officialmodelcard_164": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." } } }, { "id": "azure_ai/azure_ai/Phi-4-multimodal-instruct", "slug": "azure_ai-azure_ai-phi-4-multimodal-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-4-multimodal-instruct", "displayName": "Phi-4-multimodal-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.32, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 4, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000004, "input_cost_per_token": 8e-8, "output_cost_per_token": 3.2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 131072, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "vision": true } }, "modalities": { "supported": [ "audio", "image", "text" ], "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-4-multimodal-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112" }, "rawLitellm": { "input_cost_per_audio_token": 0.000004, "input_cost_per_token": 8e-8, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-7, "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", "supports_audio_input": true, "supports_function_calling": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/model-inference/concepts/models?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs" }, "benchmarks": { "mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_202": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "gpqa_science_phi414b_officialmodelcard_203": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "humaneval_codegeneration_phi414b_officialmodelcard_204": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "drop_reasoning_phi414b_officialmodelcard_205": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "local_mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_160": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_gpqa_science_phi414b_officialmodelcard_161": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_humaneval_codegeneration_phi414b_officialmodelcard_162": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_simpleqa_factualknowledge_phi414b_officialmodelcard_163": { "label": "SimpleQA", "category": "general_knowledge", "score": 3, "scoreText": "3.0", "metric": "Factual Knowledge", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_drop_reasoning_phi414b_officialmodelcard_164": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." } } }, { "id": "azure_ai/azure_ai/Phi-4-mini-reasoning", "slug": "azure_ai-azure_ai-phi-4-mini-reasoning", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-4-mini-reasoning", "displayName": "Phi-4-mini-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.32, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 3.2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 131072, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-4-mini-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/" }, "rawLitellm": { "input_cost_per_token": 8e-8, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_202": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "gpqa_science_phi414b_officialmodelcard_203": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "humaneval_codegeneration_phi414b_officialmodelcard_204": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "drop_reasoning_phi414b_officialmodelcard_205": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "local_mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_160": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_gpqa_science_phi414b_officialmodelcard_161": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_humaneval_codegeneration_phi414b_officialmodelcard_162": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_simpleqa_factualknowledge_phi414b_officialmodelcard_163": { "label": "SimpleQA", "category": "general_knowledge", "score": 3, "scoreText": "3.0", "metric": "Factual Knowledge", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_drop_reasoning_phi414b_officialmodelcard_164": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." } } }, { "id": "azure_ai/azure_ai/Phi-4-reasoning", "slug": "azure_ai-azure_ai-phi-4-reasoning", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "Phi-4-reasoning", "displayName": "Phi-4-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.125, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.125, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.25e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/Phi-4-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/" }, "rawLitellm": { "input_cost_per_token": 1.25e-7, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-7, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/model-inference/concepts/models?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs" }, "benchmarks": { "mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_202": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "gpqa_science_phi414b_officialmodelcard_203": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "humaneval_codegeneration_phi414b_officialmodelcard_204": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "drop_reasoning_phi414b_officialmodelcard_205": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "local_mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_160": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_gpqa_science_phi414b_officialmodelcard_161": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_humaneval_codegeneration_phi414b_officialmodelcard_162": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_simpleqa_factualknowledge_phi414b_officialmodelcard_163": { "label": "SimpleQA", "category": "general_knowledge", "score": 3, "scoreText": "3.0", "metric": "Factual Knowledge", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_drop_reasoning_phi414b_officialmodelcard_164": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." } } }, { "id": "azure_ai/azure_ai/mistral-document-ai-2505", "slug": "azure_ai-azure_ai-mistral-document-ai-2505", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "mistral-document-ai-2505", "displayName": "mistral-document-ai-2505", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": 0.003, "codeInterpreterUsdPerSession": null, "rawPricing": { "ocr_cost_per_page": 0.003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [ "/v1/ocr" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/mistral-document-ai-2505", "syncedAt": "2026-05-28", "sourceUrl": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry" }, "rawLitellm": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.003, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry", "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/mistral-document-ai-2512", "slug": "azure_ai-azure_ai-mistral-document-ai-2512", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "mistral-document-ai-2512", "displayName": "mistral-document-ai-2512", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": 0.003, "codeInterpreterUsdPerSession": null, "rawPricing": { "ocr_cost_per_page": 0.003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [ "/v1/ocr" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/mistral-document-ai-2512", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/" }, "rawLitellm": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.003, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/", "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/doc-intelligence/prebuilt-read", "slug": "azure_ai-azure_ai-doc-intelligence-prebuilt-read", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "prebuilt-read", "displayName": "prebuilt-read", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": 0.0015, "codeInterpreterUsdPerSession": null, "rawPricing": { "ocr_cost_per_page": 0.0015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [ "/v1/ocr" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/doc-intelligence/prebuilt-read", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "rawLitellm": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.0015, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/doc-intelligence/prebuilt-layout", "slug": "azure_ai-azure_ai-doc-intelligence-prebuilt-layout", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "prebuilt-layout", "displayName": "prebuilt-layout", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": 0.01, "codeInterpreterUsdPerSession": null, "rawPricing": { "ocr_cost_per_page": 0.01 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [ "/v1/ocr" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/doc-intelligence/prebuilt-layout", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "rawLitellm": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.01, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/doc-intelligence/prebuilt-document", "slug": "azure_ai-azure_ai-doc-intelligence-prebuilt-document", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "prebuilt-document", "displayName": "prebuilt-document", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": 0.01, "codeInterpreterUsdPerSession": null, "rawPricing": { "ocr_cost_per_page": 0.01 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [ "/v1/ocr" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/doc-intelligence/prebuilt-document", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "rawLitellm": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.01, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/MAI-DS-R1", "slug": "azure_ai-azure_ai-mai-ds-r1", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "MAI-DS-R1", "displayName": "MAI-DS-R1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.35, "outputUsdPer1MTokens": 5.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/MAI-DS-R1", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/" }, "rawLitellm": { "input_cost_per_token": 0.00000135, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000054, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_reasoning": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/cohere-rerank-v3-english", "slug": "azure_ai-azure_ai-cohere-rerank-v3-english", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "cohere-rerank-v3-english", "displayName": "cohere-rerank-v3-english", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 2048, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/cohere-rerank-v3-english", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/cohere-rerank-v3-multilingual", "slug": "azure_ai-azure_ai-cohere-rerank-v3-multilingual", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "cohere-rerank-v3-multilingual", "displayName": "cohere-rerank-v3-multilingual", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 2048, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/cohere-rerank-v3-multilingual", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/cohere-rerank-v3.5", "slug": "azure_ai-azure_ai-cohere-rerank-v3-5", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "cohere-rerank-v3.5", "displayName": "cohere-rerank-v3.5", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 2048, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/cohere-rerank-v3.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/cohere-rerank-v4.0-pro", "slug": "azure_ai-azure_ai-cohere-rerank-v4-0-pro", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "cohere-rerank-v4.0-pro", "displayName": "cohere-rerank-v4.0-pro", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2.5, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.0025, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 4096, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/cohere-rerank-v4.0-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "rawLitellm": { "input_cost_per_query": 0.0025, "input_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_query_tokens": 4096, "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076", "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/cohere-rerank-v4.0-fast", "slug": "azure_ai-azure_ai-cohere-rerank-v4-0-fast", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "cohere-rerank-v4.0-fast", "displayName": "cohere-rerank-v4.0-fast", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 4096, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/cohere-rerank-v4.0-fast", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "rawLitellm": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_query_tokens": 4096, "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076", "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "azure_ai/azure_ai/deepseek-v3.2", "slug": "azure_ai-azure_ai-deepseek-v3-2", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "deepseek-v3.2", "displayName": "deepseek-v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.58, "outputUsdPer1MTokens": 1.68, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.58, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.8e-7, "output_cost_per_token": 0.00000168 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/deepseek-v3.2", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549" }, "rawLitellm": { "input_cost_per_token": 5.8e-7, "litellm_provider": "azure_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000168, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "azure_ai/azure_ai/deepseek-v3.2-speciale", "slug": "azure_ai-azure_ai-deepseek-v3-2-speciale", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "deepseek-v3.2-speciale", "displayName": "deepseek-v3.2-speciale", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.58, "outputUsdPer1MTokens": 1.68, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.58, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.8e-7, "output_cost_per_token": 0.00000168 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/deepseek-v3.2-speciale", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549" }, "rawLitellm": { "input_cost_per_token": 5.8e-7, "litellm_provider": "azure_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000168, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "azure_ai/azure_ai/deepseek-r1", "slug": "azure_ai-azure_ai-deepseek-r1", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "deepseek-r1", "displayName": "deepseek-r1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.35, "outputUsdPer1MTokens": 5.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/deepseek-r1", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367" }, "rawLitellm": { "input_cost_per_token": 0.00000135, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000054, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", "supports_reasoning": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "azure_ai/azure_ai/deepseek-v3", "slug": "azure_ai-azure_ai-deepseek-v3", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "deepseek-v3", "displayName": "deepseek-v3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1400000000000001, "outputUsdPer1MTokens": 4.5600000000000005, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1400000000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000114, "output_cost_per_token": 0.00000456 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/deepseek-v3", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438" }, "rawLitellm": { "input_cost_per_token": 0.00000114, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000456, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2&viewFallbackFrom=azureml-api-1" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "azure_ai/azure_ai/deepseek-v3-0324", "slug": "azure_ai-azure_ai-deepseek-v3-0324", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "deepseek-v3-0324", "displayName": "deepseek-v3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1400000000000001, "outputUsdPer1MTokens": 4.5600000000000005, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1400000000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000114, "output_cost_per_token": 0.00000456 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/deepseek-v3-0324", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438" }, "rawLitellm": { "input_cost_per_token": 0.00000114, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000456, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "azure_ai/azure_ai/embed-v-4-0", "slug": "azure_ai-azure_ai-embed-v-4-0", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "embed-v-4-0", "displayName": "embed-v-4-0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [] }, "endpoints": [ "/v1/embeddings" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/embed-v-4-0", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image" ], "supports_embedding_image_input": true } }, { "id": "azure_ai/azure_ai/global/grok-3", "slug": "azure_ai-azure_ai-global-grok-3", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "grok-3", "displayName": "grok-3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/global/grok-3", "syncedAt": "2026-05-28", "sourceUrl": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "azure_ai/azure_ai/global/grok-3-mini", "slug": "azure_ai-azure_ai-global-grok-3-mini", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "grok-3-mini", "displayName": "grok-3-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.27, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000127 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/global/grok-3-mini", "syncedAt": "2026-05-28", "sourceUrl": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.00000127, "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "azure_ai/azure_ai/grok-3", "slug": "azure_ai-azure_ai-grok-3", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "grok-3", "displayName": "grok-3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/grok-3", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://docs.x.ai/docs/models/grok-3-fast" ], "manual_model_modalities_note": "Azure AI exact route id from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "azure_ai/azure_ai/grok-3-mini", "slug": "azure_ai-azure_ai-grok-3-mini", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "grok-3-mini", "displayName": "grok-3-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.27, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000127 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/grok-3-mini", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.00000127, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://docs.x.ai/models/grok-3-mini" ], "manual_model_modalities_note": "Azure AI exact route id from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "azure_ai/azure_ai/grok-4", "slug": "azure_ai-azure_ai-grok-4", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "grok-4", "displayName": "grok-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/grok-4", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "https://docs.x.ai/developers/models/grok-4" ], "manual_model_modalities_note": "Azure AI exact route id from official docs" }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "azure_ai/azure_ai/grok-4-fast-non-reasoning", "slug": "azure_ai-azure_ai-grok-4-fast-non-reasoning", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "grok-4-fast-non-reasoning", "displayName": "grok-4-fast-non-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/grok-4-fast-non-reasoning", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "azure_ai/azure_ai/grok-4-fast-reasoning", "slug": "azure_ai-azure_ai-grok-4-fast-reasoning", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "grok-4-fast-reasoning", "displayName": "grok-4-fast-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/grok-4-fast-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/" }, "rawLitellm": { "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "azure_ai/azure_ai/grok-4-1-fast-non-reasoning", "slug": "azure_ai-azure_ai-grok-4-1-fast-non-reasoning", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "grok-4-1-fast-non-reasoning", "displayName": "grok-4-1-fast-non-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/grok-4-1-fast-non-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964" }, "rawLitellm": { "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "azure_ai/azure_ai/grok-4-1-fast-reasoning", "slug": "azure_ai-azure_ai-grok-4-1-fast-reasoning", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "grok-4-1-fast-reasoning", "displayName": "grok-4-1-fast-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/grok-4-1-fast-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964" }, "rawLitellm": { "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "azure_ai/azure_ai/grok-code-fast-1", "slug": "azure_ai-azure_ai-grok-code-fast-1", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "grok-code-fast-1", "displayName": "grok-code-fast-1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/grok-code-fast-1", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/jais-30b-chat", "slug": "azure_ai-azure_ai-jais-30b-chat", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "jais-30b-chat", "displayName": "jais-30b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3200, "outputUsdPer1MTokens": 9710, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3200, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0032, "output_cost_per_token": 0.00971 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/jais-30b-chat", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat" }, "rawLitellm": { "input_cost_per_token": 0.0032, "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00971, "source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2&viewFallbackFrom=azureml-api-1#core42" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/jamba-instruct", "slug": "azure_ai-azure_ai-jamba-instruct", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "jamba-instruct", "displayName": "jamba-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 7e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 70000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/jamba-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 70000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/model-lifecycle-retirement", "https://docs.ai21.com/docs/prompt-engineering", "https://docs.ai21.com/reference/jamba-1-6-api-ref" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/kimi-k2.5", "slug": "azure_ai-azure_ai-kimi-k2-5", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "kimi-k2.5", "displayName": "kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "video_input": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321", "supports_function_calling": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=azureml-api-2" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "azure_ai/azure_ai/ministral-3b", "slug": "azure_ai-azure_ai-ministral-3b", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "ministral-3b", "displayName": "ministral-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.04, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/ministral-3b", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview" }, "rawLitellm": { "input_cost_per_token": 4e-8, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-8, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2&viewFallbackFrom=azureml-api-1#core42" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/mistral-large", "slug": "azure_ai-azure_ai-mistral-large", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "mistral-large", "displayName": "mistral-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 4, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000012 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/mistral-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000004, "litellm_provider": "azure_ai", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000012, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2&viewFallbackFrom=azureml-api-1#core42" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/mistral-large-2407", "slug": "azure_ai-azure_ai-mistral-large-2407", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "mistral-large-2407", "displayName": "mistral-large-2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/mistral-large-2407", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2&viewFallbackFrom=azureml-api-1#core42" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/mistral-large-latest", "slug": "azure_ai-azure_ai-mistral-large-latest", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "mistral-large-latest", "displayName": "mistral-large-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/mistral-large-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/resources/changelogs", "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2&viewFallbackFrom=azureml-api-1#core42" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/mistral-large-3", "slug": "azure_ai-azure_ai-mistral-large-3", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "mistral-large-3", "displayName": "mistral-large-3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 256000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/mistral-large-3", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "mmlu_accuracy_mistrallarge3_benchmarkleaderboard_118": { "label": "MMLU", "category": "general_knowledge", "score": 85.5, "scoreText": "85.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "mmlupro_accuracy_mistrallarge3_benchmarkleaderboard_119": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 78, "scoreText": "78.0", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "gpqadiamond_accuracy_mistrallarge3_benchmarkleaderboard_120": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 43.9, "scoreText": "43.9", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "humaneval_pass1_mistrallarge3_benchmarkleaderboard_121": { "label": "HumanEval", "category": "coding", "score": 92, "scoreText": "92.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "math500_accuracy_mistrallarge3_benchmarkleaderboard_122": { "label": "MATH-500", "category": "math", "score": 93.6, "scoreText": "93.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "aime2024_accuracy_mistrallarge3_benchmarkleaderboard_123": { "label": "AIME 2024", "category": "math", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "aime2025_accuracy_mistrallarge3_benchmarkleaderboard_124": { "label": "AIME 2025", "category": "math", "score": 40, "scoreText": "40.0", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "simpleqa_accuracy_mistrallarge3_benchmarkleaderboard_125": { "label": "SimpleQA", "category": "general_knowledge", "score": 23.8, "scoreText": "23.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." } } }, { "id": "azure_ai/azure_ai/mistral-medium-2505", "slug": "azure_ai-azure_ai-mistral-medium-2505", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "mistral-medium-2505", "displayName": "mistral-medium-2505", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 131072, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/mistral-medium-2505", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000002, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2&viewFallbackFrom=azureml-api-1#core42" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/mistral-nemo", "slug": "azure_ai-azure_ai-mistral-nemo", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "mistral-nemo", "displayName": "mistral-nemo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 131072, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/mistral-nemo", "syncedAt": "2026-05-28", "sourceUrl": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-7, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2&viewFallbackFrom=azureml-api-1" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "azure_ai/azure_ai/mistral-small", "slug": "azure_ai-azure_ai-mistral-small", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "mistral-small", "displayName": "mistral-small", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/mistral-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "azure_ai", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2&viewFallbackFrom=azureml-api-1" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "azure_ai/azure_ai/mistral-small-2503", "slug": "azure_ai-azure_ai-mistral-small-2503", "provider": "azure_ai", "providerSlug": "azure_ai", "name": "mistral-small-2503", "displayName": "mistral-small-2503", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure_ai/mistral-small-2503", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://learn.microsoft.com/en-us/azure/machine-learning/concept-models-featured?view=azureml-api-2&viewFallbackFrom=azureml-api-1" ], "manual_model_modalities_note": "Azure AI exact route id from official docs." } }, { "id": "text-completion-openai/babbage-002", "slug": "text-completion-openai-babbage-002", "provider": "text-completion-openai", "providerSlug": "text-completion-openai", "name": "babbage-002", "displayName": "babbage-002", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "babbage-002", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 4e-7 } }, { "id": "bedrock/bedrock/*/1-month-commitment/cohere.command-light-text-v14", "slug": "bedrock-bedrock-1-month-commitment-cohere-command-light-text-v14", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.command-light-text-v14", "displayName": "cohere.command-light-text-v14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.001902, "perSecondOutputUsd": 0.001902, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.001902, "output_cost_per_second": 0.001902 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/*/1-month-commitment/cohere.command-light-text-v14", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.001902, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_second": 0.001902, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact commitment alias from official docs." } }, { "id": "bedrock/bedrock/*/1-month-commitment/cohere.command-text-v14", "slug": "bedrock-bedrock-1-month-commitment-cohere-command-text-v14", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.command-text-v14", "displayName": "cohere.command-text-v14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.011, "perSecondOutputUsd": 0.011, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.011, "output_cost_per_second": 0.011 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/*/1-month-commitment/cohere.command-text-v14", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_second": 0.011, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact commitment alias from official docs." } }, { "id": "bedrock/bedrock/*/6-month-commitment/cohere.command-light-text-v14", "slug": "bedrock-bedrock-6-month-commitment-cohere-command-light-text-v14", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.command-light-text-v14", "displayName": "cohere.command-light-text-v14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0011416, "perSecondOutputUsd": 0.0011416, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0011416, "output_cost_per_second": 0.0011416 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/*/6-month-commitment/cohere.command-light-text-v14", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0011416, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_second": 0.0011416, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact commitment alias from official docs." } }, { "id": "bedrock/bedrock/*/6-month-commitment/cohere.command-text-v14", "slug": "bedrock-bedrock-6-month-commitment-cohere-command-text-v14", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.command-text-v14", "displayName": "cohere.command-text-v14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0066027, "perSecondOutputUsd": 0.0066027, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0066027, "output_cost_per_second": 0.0066027 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/*/6-month-commitment/cohere.command-text-v14", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0066027, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_second": 0.0066027, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact commitment alias from official docs." } }, { "id": "bedrock/bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-ap-northeast-1-1-month-commitment-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.01475, "perSecondOutputUsd": 0.01475, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.01475, "output_cost_per_second": 0.01475 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.01475, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.01475, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude Instant commitment variant from official docs" } }, { "id": "bedrock/bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1", "slug": "bedrock-bedrock-ap-northeast-1-1-month-commitment-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0455, "perSecondOutputUsd": 0.0455, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0455, "output_cost_per_second": 0.0455 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.0455 } }, { "id": "bedrock/bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1", "slug": "bedrock-bedrock-ap-northeast-1-1-month-commitment-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0455, "perSecondOutputUsd": 0.0455, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0455, "output_cost_per_second": 0.0455 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.0455, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude 2.1 commitment variant from official docs" } }, { "id": "bedrock/bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-ap-northeast-1-6-month-commitment-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.008194, "perSecondOutputUsd": 0.008194, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.008194, "output_cost_per_second": 0.008194 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.008194, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.008194, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude Instant commitment variant from official docs" } }, { "id": "bedrock/bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1", "slug": "bedrock-bedrock-ap-northeast-1-6-month-commitment-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.02527, "perSecondOutputUsd": 0.02527, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.02527, "output_cost_per_second": 0.02527 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.02527 } }, { "id": "bedrock/bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1", "slug": "bedrock-bedrock-ap-northeast-1-6-month-commitment-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.02527, "perSecondOutputUsd": 0.02527, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.02527, "output_cost_per_second": 0.02527 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.02527, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude 2.1 commitment variant from official docs" } }, { "id": "bedrock/bedrock/ap-northeast-1/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-ap-northeast-1-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.23, "outputUsdPer1MTokens": 7.55, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.23, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000223, "output_cost_per_token": 0.00000755 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000223, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.00000755, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact regional Anthropic route id from official docs." } }, { "id": "bedrock/bedrock/ap-northeast-1/anthropic.claude-v1", "slug": "bedrock-bedrock-ap-northeast-1-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_tool_choice": true } }, { "id": "bedrock/bedrock/ap-northeast-1/anthropic.claude-v2:1", "slug": "bedrock-bedrock-ap-northeast-1-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/en_us/bedrock/latest/userguide/model-parameters-anthropic-claude-text-completion.html", "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact regional Anthropic Claude 2.1 route id from official docs." } }, { "id": "bedrock/bedrock/ap-northeast-1/deepseek.v3.2", "slug": "bedrock-bedrock-ap-northeast-1-deepseek-v3-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "deepseek.v3.2", "displayName": "deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.74, "outputUsdPer1MTokens": 2.2199999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.74, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/deepseek.v3.2", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.4e-7, "litellm_provider": "bedrock", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000222, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" ], "manual_model_modalities_note": "Bedrock exact DeepSeek route id from official docs" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock/bedrock/ap-northeast-1/minimax.minimax-m2.1", "slug": "bedrock-bedrock-ap-northeast-1-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/ap-northeast-1/minimax.minimax-m2.5", "slug": "bedrock-bedrock-ap-northeast-1-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.00000144, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking", "slug": "bedrock-bedrock-ap-northeast-1-moonshotai-kimi-k2-thinking", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2-thinking", "displayName": "moonshotai.kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.73, "outputUsdPer1MTokens": 3.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.73, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.3e-7, "output_cost_per_token": 0.00000303 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.3e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.00000303, "supports_function_calling": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs" } }, { "id": "bedrock/bedrock/ap-northeast-1/moonshotai.kimi-k2.5", "slug": "bedrock-bedrock-ap-northeast-1-moonshotai-kimi-k2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2.5", "displayName": "moonshotai.kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 3.5999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 0.0000036 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/moonshotai.kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000036, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs" }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "bedrock/bedrock/ap-northeast-1/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-ap-northeast-1-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-northeast-1/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/moonshotai.kimi-k2-thinking", "slug": "bedrock-bedrock-moonshotai-kimi-k2-thinking", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2-thinking", "displayName": "moonshotai.kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.73, "outputUsdPer1MTokens": 3.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.73, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.3e-7, "output_cost_per_token": 0.00000303 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/moonshotai.kimi-k2-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.3e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.00000303, "supports_function_calling": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs." } }, { "id": "bedrock/bedrock/moonshotai.kimi-k2.5", "slug": "bedrock-bedrock-moonshotai-kimi-k2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2.5", "displayName": "moonshotai.kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000303 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/moonshotai.kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.00000303, "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs." }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "bedrock/bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0", "slug": "bedrock-bedrock-ap-south-1-meta-llama3-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-70b-instruct-v1:0", "displayName": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.18, "outputUsdPer1MTokens": 4.199999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000318, "output_cost_per_token": 0.0000042 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000318, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000042, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0", "slug": "bedrock-bedrock-ap-south-1-meta-llama3-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-8b-instruct-v1:0", "displayName": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/ap-south-1/deepseek.v3.2", "slug": "bedrock-bedrock-ap-south-1-deepseek-v3-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "deepseek.v3.2", "displayName": "deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.74, "outputUsdPer1MTokens": 2.2199999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.74, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-south-1/deepseek.v3.2", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.4e-7, "litellm_provider": "bedrock", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000222, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" ], "manual_model_modalities_note": "Bedrock exact DeepSeek route id from official docs" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock/bedrock/ap-south-1/minimax.minimax-m2.1", "slug": "bedrock-bedrock-ap-south-1-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-south-1/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/ap-south-1/minimax.minimax-m2.5", "slug": "bedrock-bedrock-ap-south-1-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-south-1/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.00000144, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/ap-south-1/moonshotai.kimi-k2-thinking", "slug": "bedrock-bedrock-ap-south-1-moonshotai-kimi-k2-thinking", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2-thinking", "displayName": "moonshotai.kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.71, "outputUsdPer1MTokens": 2.94, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.71, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.1e-7, "output_cost_per_token": 0.00000294 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-south-1/moonshotai.kimi-k2-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.1e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.00000294, "supports_function_calling": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" ], "manual_model_modalities_note": "Bedrock exact regional Moonshot route id from official docs." } }, { "id": "bedrock/bedrock/ap-south-1/moonshotai.kimi-k2.5", "slug": "bedrock-bedrock-ap-south-1-moonshotai-kimi-k2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2.5", "displayName": "moonshotai.kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 3.5999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 0.0000036 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-south-1/moonshotai.kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000036, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs" }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "bedrock/bedrock/ap-south-1/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-ap-south-1-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-south-1/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/ap-southeast-2/minimax.minimax-m2.5", "slug": "bedrock-bedrock-ap-southeast-2-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.309, "outputUsdPer1MTokens": 1.236, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.309, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.09e-7, "output_cost_per_token": 0.000001236 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-southeast-2/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.09e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.000001236, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/ap-southeast-3/deepseek.v3.2", "slug": "bedrock-bedrock-ap-southeast-3-deepseek-v3-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "deepseek.v3.2", "displayName": "deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.74, "outputUsdPer1MTokens": 2.2199999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.74, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-southeast-3/deepseek.v3.2", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.4e-7, "litellm_provider": "bedrock", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000222, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" ], "manual_model_modalities_note": "Bedrock exact DeepSeek route id from official docs" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock/bedrock/ap-southeast-3/minimax.minimax-m2.1", "slug": "bedrock-bedrock-ap-southeast-3-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-southeast-3/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/ap-southeast-3/minimax.minimax-m2.5", "slug": "bedrock-bedrock-ap-southeast-3-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-southeast-3/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.00000144, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/ap-southeast-3/moonshotai.kimi-k2.5", "slug": "bedrock-bedrock-ap-southeast-3-moonshotai-kimi-k2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2.5", "displayName": "moonshotai.kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 3.5999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 0.0000036 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-southeast-3/moonshotai.kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000036, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs" }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "bedrock/bedrock/ap-southeast-3/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-ap-southeast-3-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ap-southeast-3/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0", "slug": "bedrock-bedrock-ca-central-1-meta-llama3-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-70b-instruct-v1:0", "displayName": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.05, "outputUsdPer1MTokens": 4.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.05, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000305, "output_cost_per_token": 0.00000403 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000305, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000403, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0", "slug": "bedrock-bedrock-ca-central-1-meta-llama3-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-8b-instruct-v1:0", "displayName": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 0.69, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 6.9e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.9e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/eu-north-1/deepseek.v3.2", "slug": "bedrock-bedrock-eu-north-1-deepseek-v3-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "deepseek.v3.2", "displayName": "deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.74, "outputUsdPer1MTokens": 2.2199999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.74, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-north-1/deepseek.v3.2", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.4e-7, "litellm_provider": "bedrock", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000222, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" ], "manual_model_modalities_note": "Bedrock exact DeepSeek route id from official docs" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock/bedrock/eu-north-1/minimax.minimax-m2.1", "slug": "bedrock-bedrock-eu-north-1-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-north-1/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/eu-north-1/minimax.minimax-m2.5", "slug": "bedrock-bedrock-eu-north-1-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-north-1/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.00000144, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/eu-north-1/moonshotai.kimi-k2.5", "slug": "bedrock-bedrock-eu-north-1-moonshotai-kimi-k2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2.5", "displayName": "moonshotai.kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 3.5999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 0.0000036 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-north-1/moonshotai.kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000036, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs" }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "bedrock/bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-eu-central-1-1-month-commitment-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.01635, "perSecondOutputUsd": 0.01635, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.01635, "output_cost_per_second": 0.01635 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.01635, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.01635, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude Instant commitment variant from official docs" } }, { "id": "bedrock/bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1", "slug": "bedrock-bedrock-eu-central-1-1-month-commitment-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0415, "perSecondOutputUsd": 0.0415, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0415, "output_cost_per_second": 0.0415 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.0415 } }, { "id": "bedrock/bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1", "slug": "bedrock-bedrock-eu-central-1-1-month-commitment-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0415, "perSecondOutputUsd": 0.0415, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0415, "output_cost_per_second": 0.0415 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.0415, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude 2.1 commitment variant from official docs" } }, { "id": "bedrock/bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-eu-central-1-6-month-commitment-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.009083, "perSecondOutputUsd": 0.009083, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.009083, "output_cost_per_second": 0.009083 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.009083, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.009083, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude Instant commitment variant from official docs" } }, { "id": "bedrock/bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1", "slug": "bedrock-bedrock-eu-central-1-6-month-commitment-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.02305, "perSecondOutputUsd": 0.02305, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.02305, "output_cost_per_second": 0.02305 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.02305, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://aws-blogs-artifacts-public.s3.amazonaws.com/ML-15986/AmazonBedrock_UserGuide.pdf", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-claude.html" ], "manual_model_modalities_note": "Bedrock exact regional commitment alias from official docs." } }, { "id": "bedrock/bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1", "slug": "bedrock-bedrock-eu-central-1-6-month-commitment-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.02305, "perSecondOutputUsd": 0.02305, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.02305, "output_cost_per_second": 0.02305 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.02305, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude 2.1 commitment variant from official docs" } }, { "id": "bedrock/bedrock/eu-central-1/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-eu-central-1-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.48, "outputUsdPer1MTokens": 8.379999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.48, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000248, "output_cost_per_token": 0.00000838 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000248, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.00000838, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact regional Anthropic route id from official docs." } }, { "id": "bedrock/bedrock/eu-central-1/anthropic.claude-v1", "slug": "bedrock-bedrock-eu-central-1-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://aws-blogs-artifacts-public.s3.amazonaws.com/ML-15986/AmazonBedrock_UserGuide.pdf", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-claude.html" ], "manual_model_modalities_note": "Bedrock exact regional alias from official docs." } }, { "id": "bedrock/bedrock/eu-central-1/anthropic.claude-v2:1", "slug": "bedrock-bedrock-eu-central-1-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact regional Anthropic Claude 2.1 route id from official docs." } }, { "id": "bedrock/bedrock/eu-central-1/minimax.minimax-m2.1", "slug": "bedrock-bedrock-eu-central-1-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/eu-central-1/minimax.minimax-m2.5", "slug": "bedrock-bedrock-eu-central-1-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.00000144, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/eu-central-1/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-eu-central-1-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-central-1/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0", "slug": "bedrock-bedrock-eu-west-1-meta-llama3-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-70b-instruct-v1:0", "displayName": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.8600000000000003, "outputUsdPer1MTokens": 3.78, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.8600000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000286, "output_cost_per_token": 0.00000378 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000286, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000378, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0", "slug": "bedrock-bedrock-eu-west-1-meta-llama3-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-8b-instruct-v1:0", "displayName": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.32, "outputUsdPer1MTokens": 0.65, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.32, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.2e-7, "output_cost_per_token": 6.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.5e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/eu-west-1/minimax.minimax-m2.1", "slug": "bedrock-bedrock-eu-west-1-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-1/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/eu-west-1/minimax.minimax-m2.5", "slug": "bedrock-bedrock-eu-west-1-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-1/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.00000144, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/eu-west-1/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-eu-west-1-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-1/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0", "slug": "bedrock-bedrock-eu-west-2-meta-llama3-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-70b-instruct-v1:0", "displayName": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.45, "outputUsdPer1MTokens": 4.55, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.45, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000345, "output_cost_per_token": 0.00000455 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000345, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000455, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0", "slug": "bedrock-bedrock-eu-west-2-meta-llama3-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-8b-instruct-v1:0", "displayName": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39, "outputUsdPer1MTokens": 0.78, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.9e-7, "output_cost_per_token": 7.8e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.9e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.8e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/eu-west-2/minimax.minimax-m2.1", "slug": "bedrock-bedrock-eu-west-2-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.47, "outputUsdPer1MTokens": 1.8599999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.47, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.7e-7, "output_cost_per_token": 0.00000186 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-2/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 4.7e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000186, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/eu-west-2/minimax.minimax-m2.5", "slug": "bedrock-bedrock-eu-west-2-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.47, "outputUsdPer1MTokens": 1.8599999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.47, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.7e-7, "output_cost_per_token": 0.00000186 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-2/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 4.7e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.00000186, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/eu-west-2/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-eu-west-2-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.78, "outputUsdPer1MTokens": 1.8599999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.78, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.8e-7, "output_cost_per_token": 0.00000186 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-2/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.8e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000186, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2", "slug": "bedrock-bedrock-eu-west-3-mistral-mistral-7b-instruct-v0-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mistral-7b-instruct-v0:2", "displayName": "mistral.mistral-7b-instruct-v0:2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.26, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2.6e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.6e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "bedrock/bedrock/eu-west-3/mistral.mistral-large-2402-v1:0", "slug": "bedrock-bedrock-eu-west-3-mistral-mistral-large-2402-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mistral-large-2402-v1:0", "displayName": "mistral.mistral-large-2402-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10.4, "outputUsdPer1MTokens": 31.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10.4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000104, "output_cost_per_token": 0.0000312 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000104, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0000312, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" } }, { "id": "bedrock/bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1", "slug": "bedrock-bedrock-eu-west-3-mistral-mixtral-8x7b-instruct-v0-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mixtral-8x7b-instruct-v0:1", "displayName": "mistral.mixtral-8x7b-instruct-v0:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.59, "outputUsdPer1MTokens": 0.9099999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.59, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.9e-7, "output_cost_per_token": 9.1e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5.9e-7, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 9.1e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" } }, { "id": "bedrock/bedrock/eu-south-1/minimax.minimax-m2.1", "slug": "bedrock-bedrock-eu-south-1-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-south-1/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/eu-south-1/minimax.minimax-m2.5", "slug": "bedrock-bedrock-eu-south-1-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-south-1/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.00000144, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/eu-south-1/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-eu-south-1-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/eu-south-1/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0", "slug": "bedrock-bedrock-invoke-anthropic-claude-3-5-sonnet-20240620-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-5-sonnet-20240620-v1:0", "displayName": "anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Anthropic via Invoke route does not currently support pdf input." }, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact invoke alias from official docs." }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0", "slug": "bedrock-bedrock-sa-east-1-meta-llama3-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-70b-instruct-v1:0", "displayName": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 4.45, "outputUsdPer1MTokens": 5.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 4.45, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000445, "output_cost_per_token": 0.00000588 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000445, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000588, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0", "slug": "bedrock-bedrock-sa-east-1-meta-llama3-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-8b-instruct-v1:0", "displayName": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.01, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.00000101 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000101, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/sa-east-1/deepseek.v3.2", "slug": "bedrock-bedrock-sa-east-1-deepseek-v3-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "deepseek.v3.2", "displayName": "deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.74, "outputUsdPer1MTokens": 2.2199999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.74, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/sa-east-1/deepseek.v3.2", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.4e-7, "litellm_provider": "bedrock", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000222, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" ], "manual_model_modalities_note": "Bedrock exact DeepSeek route id from official docs" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock/bedrock/sa-east-1/minimax.minimax-m2.1", "slug": "bedrock-bedrock-sa-east-1-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/sa-east-1/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs." }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/sa-east-1/minimax.minimax-m2.5", "slug": "bedrock-bedrock-sa-east-1-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.36, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.36, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/sa-east-1/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.00000144, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/sa-east-1/moonshotai.kimi-k2-thinking", "slug": "bedrock-bedrock-sa-east-1-moonshotai-kimi-k2-thinking", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2-thinking", "displayName": "moonshotai.kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.73, "outputUsdPer1MTokens": 3.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.73, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.3e-7, "output_cost_per_token": 0.00000303 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/sa-east-1/moonshotai.kimi-k2-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.3e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.00000303, "supports_function_calling": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs" } }, { "id": "bedrock/bedrock/sa-east-1/moonshotai.kimi-k2.5", "slug": "bedrock-bedrock-sa-east-1-moonshotai-kimi-k2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2.5", "displayName": "moonshotai.kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 3.5999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 0.0000036 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/sa-east-1/moonshotai.kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000036, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs" }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "bedrock/bedrock/sa-east-1/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-sa-east-1-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.44, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/sa-east-1/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000144, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-us-east-1-1-month-commitment-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.011, "perSecondOutputUsd": 0.011, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.011, "output_cost_per_second": 0.011 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.011, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude Instant commitment variant from official docs" } }, { "id": "bedrock/bedrock/us-east-1/1-month-commitment/anthropic.claude-v1", "slug": "bedrock-bedrock-us-east-1-1-month-commitment-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0175, "perSecondOutputUsd": 0.0175, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0175, "output_cost_per_second": 0.0175 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.0175, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://aws-blogs-artifacts-public.s3.amazonaws.com/ML-15986/AmazonBedrock_UserGuide.pdf", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-claude.html" ], "manual_model_modalities_note": "Bedrock exact regional commitment alias from official docs." } }, { "id": "bedrock/bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1", "slug": "bedrock-bedrock-us-east-1-1-month-commitment-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0175, "perSecondOutputUsd": 0.0175, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0175, "output_cost_per_second": 0.0175 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.0175, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude 2.1 commitment variant from official docs" } }, { "id": "bedrock/bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-us-east-1-6-month-commitment-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00611, "perSecondOutputUsd": 0.00611, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00611, "output_cost_per_second": 0.00611 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.00611, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude Instant commitment variant from official docs" } }, { "id": "bedrock/bedrock/us-east-1/6-month-commitment/anthropic.claude-v1", "slug": "bedrock-bedrock-us-east-1-6-month-commitment-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00972, "perSecondOutputUsd": 0.00972, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00972, "output_cost_per_second": 0.00972 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.00972, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://aws-blogs-artifacts-public.s3.amazonaws.com/ML-15986/AmazonBedrock_UserGuide.pdf", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-claude.html" ], "manual_model_modalities_note": "Bedrock exact regional commitment alias from official docs." } }, { "id": "bedrock/bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1", "slug": "bedrock-bedrock-us-east-1-6-month-commitment-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00972, "perSecondOutputUsd": 0.00972, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00972, "output_cost_per_second": 0.00972 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.00972, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude 2.1 commitment variant from official docs" } }, { "id": "bedrock/bedrock/us-east-1/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-us-east-1-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0000024, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact regional Anthropic route id from official docs." } }, { "id": "bedrock/bedrock/us-east-1/anthropic.claude-v1", "slug": "bedrock-bedrock-us-east-1-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://aws-blogs-artifacts-public.s3.amazonaws.com/ML-15986/AmazonBedrock_UserGuide.pdf" ], "manual_model_modalities_note": "Bedrock exact regional alias from official docs." } }, { "id": "bedrock/bedrock/us-east-1/anthropic.claude-v2:1", "slug": "bedrock-bedrock-us-east-1-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact regional Anthropic Claude 2.1 route id from official docs." } }, { "id": "bedrock/bedrock/us-east-1/meta.llama3-70b-instruct-v1:0", "slug": "bedrock-bedrock-us-east-1-meta-llama3-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-70b-instruct-v1:0", "displayName": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.65, "outputUsdPer1MTokens": 3.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000265, "output_cost_per_token": 0.0000035 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000265, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000035, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/us-east-1/meta.llama3-8b-instruct-v1:0", "slug": "bedrock-bedrock-us-east-1-meta-llama3-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-8b-instruct-v1:0", "displayName": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2", "slug": "bedrock-bedrock-us-east-1-mistral-mistral-7b-instruct-v0-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mistral-7b-instruct-v0:2", "displayName": "mistral.mistral-7b-instruct-v0:2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "bedrock/bedrock/us-east-1/mistral.mistral-large-2402-v1:0", "slug": "bedrock-bedrock-us-east-1-mistral-mistral-large-2402-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mistral-large-2402-v1:0", "displayName": "mistral.mistral-large-2402-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/mistral.mistral-large-2402-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" } }, { "id": "bedrock/bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1", "slug": "bedrock-bedrock-us-east-1-mistral-mixtral-8x7b-instruct-v0-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mixtral-8x7b-instruct-v0:1", "displayName": "mistral.mixtral-8x7b-instruct-v0:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.44999999999999996, "outputUsdPer1MTokens": 0.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.44999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.5e-7, "output_cost_per_token": 7e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 7e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" } }, { "id": "bedrock/bedrock/us-east-1/deepseek.v3.2", "slug": "bedrock-bedrock-us-east-1-deepseek-v3-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "deepseek.v3.2", "displayName": "deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.62, "outputUsdPer1MTokens": 1.85, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.62, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/deepseek.v3.2", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000185, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" ], "manual_model_modalities_note": "Bedrock exact DeepSeek route id from official docs" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock/bedrock/us-east-1/minimax.minimax-m2.1", "slug": "bedrock-bedrock-us-east-1-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs." }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/us-east-1/minimax.minimax-m2.5", "slug": "bedrock-bedrock-us-east-1-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs." }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/us-east-1/moonshotai.kimi-k2-thinking", "slug": "bedrock-bedrock-us-east-1-moonshotai-kimi-k2-thinking", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2-thinking", "displayName": "moonshotai.kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/moonshotai.kimi-k2-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000025, "supports_function_calling": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" ], "manual_model_modalities_note": "Bedrock-mantle us-east-1 alias is documented with text input and text output." } }, { "id": "bedrock/bedrock/us-east-1/moonshotai.kimi-k2.5", "slug": "bedrock-bedrock-us-east-1-moonshotai-kimi-k2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2.5", "displayName": "moonshotai.kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/moonshotai.kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs." }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "bedrock/bedrock/us-east-1/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-us-east-1-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/us-east-2/deepseek.v3.2", "slug": "bedrock-bedrock-us-east-2-deepseek-v3-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "deepseek.v3.2", "displayName": "deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.62, "outputUsdPer1MTokens": 1.85, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.62, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-2/deepseek.v3.2", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000185, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" ], "manual_model_modalities_note": "Bedrock exact DeepSeek route id from official docs." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock/bedrock/us-east-2/minimax.minimax-m2.1", "slug": "bedrock-bedrock-us-east-2-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-2/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs." }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/us-east-2/minimax.minimax-m2.5", "slug": "bedrock-bedrock-us-east-2-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-2/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "output_cost_per_token": 0.0000012, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs." }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/us-east-2/moonshotai.kimi-k2-thinking", "slug": "bedrock-bedrock-us-east-2-moonshotai-kimi-k2-thinking", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2-thinking", "displayName": "moonshotai.kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-2/moonshotai.kimi-k2-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000025, "supports_function_calling": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs." } }, { "id": "bedrock/bedrock/us-east-2/moonshotai.kimi-k2.5", "slug": "bedrock-bedrock-us-east-2-moonshotai-kimi-k2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2.5", "displayName": "moonshotai.kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-2/moonshotai.kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs." }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "bedrock/bedrock/us-east-2/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-us-east-2-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-2/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/us-gov-east-1/amazon.nova-pro-v1:0", "slug": "bedrock-bedrock-us-gov-east-1-amazon-nova-pro-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.nova-pro-v1:0", "displayName": "amazon.nova-pro-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.96, "outputUsdPer1MTokens": 3.84, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.96, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9.6e-7, "output_cost_per_token": 0.00000384 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/amazon.nova-pro-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 0.00000384, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-pro.html" ], "manual_model_modalities_note": "Bedrock exact GovCloud alias from official docs." } }, { "id": "bedrock/bedrock/us-gov-east-1/amazon.titan-embed-text-v1", "slug": "bedrock-bedrock-us-gov-east-1-amazon-titan-embed-text-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-embed-text-v1", "displayName": "amazon.titan-embed-text-v1", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1536, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/amazon.titan-embed-text-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1536 } }, { "id": "bedrock/bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0", "slug": "bedrock-bedrock-us-gov-east-1-amazon-titan-embed-text-v2-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-embed-text-v2:0", "displayName": "amazon.titan-embed-text-v2:0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024 } }, { "id": "bedrock/bedrock/us-gov-east-1/amazon.titan-text-express-v1", "slug": "bedrock-bedrock-us-gov-east-1-amazon-titan-text-express-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-text-express-v1", "displayName": "amazon.titan-text-express-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.3, "outputUsdPer1MTokens": 1.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000013, "output_cost_per_token": 0.0000017 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 42000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/amazon.titan-text-express-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000013, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.0000017, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Amazon Titan route id from official docs." } }, { "id": "bedrock/bedrock/us-gov-east-1/amazon.titan-text-lite-v1", "slug": "bedrock-bedrock-us-gov-east-1-amazon-titan-text-lite-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-text-lite-v1", "displayName": "amazon.titan-text-lite-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 42000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/amazon.titan-text-lite-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Amazon Titan route id from official docs." } }, { "id": "bedrock/bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0", "slug": "bedrock-bedrock-us-gov-east-1-amazon-titan-text-premier-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-text-premier-v1:0", "displayName": "amazon.titan-text-premier-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 42000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0000015, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Amazon Titan route id from official docs." } }, { "id": "bedrock/bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "slug": "bedrock-bedrock-us-gov-east-1-anthropic-claude-3-5-sonnet-20240620-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-5-sonnet-20240620-v1:0", "displayName": "anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.5999999999999996, "outputUsdPer1MTokens": 18, "cachedInputUsdPer1MTokens": 0.36, "cacheWriteUsdPer1MTokens": 4.5, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.5999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018, "cache_read_input_token_cost": 3.6e-7, "cache_creation_input_token_cost": 0.0000045 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000036, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000018, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3.6e-7, "cache_creation_input_token_cost": 0.0000045, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Anthropic route id from official docs." }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0", "slug": "bedrock-bedrock-us-gov-east-1-anthropic-claude-3-haiku-20240307-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-haiku-20240307-v1:0", "displayName": "anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": 0.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Anthropic route id from official docs." } }, { "id": "bedrock/bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock-bedrock-us-gov-east-1-anthropic-claude-sonnet-4-5-20250929-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000165, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Anthropic route id from official docs." }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock-bedrock-us-gov-east-1-claude-sonnet-4-5-20250929-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "claude-sonnet-4-5-20250929-v1:0", "displayName": "claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000165, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud alias from official docs." }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0", "slug": "bedrock-bedrock-us-gov-east-1-meta-llama3-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-70b-instruct-v1:0", "displayName": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.65, "outputUsdPer1MTokens": 3.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000265, "output_cost_per_token": 0.0000035 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 8000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "pdf_input": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000265, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.0000035, "supports_pdf_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0", "slug": "bedrock-bedrock-us-gov-east-1-meta-llama3-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-8b-instruct-v1:0", "displayName": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.65, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.00000265 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 8000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "pdf_input": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.00000265, "supports_pdf_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/us-gov-west-1/amazon.nova-pro-v1:0", "slug": "bedrock-bedrock-us-gov-west-1-amazon-nova-pro-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.nova-pro-v1:0", "displayName": "amazon.nova-pro-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.96, "outputUsdPer1MTokens": 3.84, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.96, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9.6e-7, "output_cost_per_token": 0.00000384 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/amazon.nova-pro-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 0.00000384, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el", "https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Amazon Nova route id from official docs." } }, { "id": "bedrock/bedrock/us-gov-west-1/amazon.titan-embed-text-v1", "slug": "bedrock-bedrock-us-gov-west-1-amazon-titan-embed-text-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-embed-text-v1", "displayName": "amazon.titan-embed-text-v1", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1536, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/amazon.titan-embed-text-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1536 } }, { "id": "bedrock/bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0", "slug": "bedrock-bedrock-us-gov-west-1-amazon-titan-embed-text-v2-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-embed-text-v2:0", "displayName": "amazon.titan-embed-text-v2:0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024 } }, { "id": "bedrock/bedrock/us-gov-west-1/amazon.titan-text-express-v1", "slug": "bedrock-bedrock-us-gov-west-1-amazon-titan-text-express-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-text-express-v1", "displayName": "amazon.titan-text-express-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.3, "outputUsdPer1MTokens": 1.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000013, "output_cost_per_token": 0.0000017 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 42000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/amazon.titan-text-express-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000013, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.0000017, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Amazon Titan route id from official docs." } }, { "id": "bedrock/bedrock/us-gov-west-1/amazon.titan-text-lite-v1", "slug": "bedrock-bedrock-us-gov-west-1-amazon-titan-text-lite-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-text-lite-v1", "displayName": "amazon.titan-text-lite-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 42000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/amazon.titan-text-lite-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Amazon Titan route id from official docs." } }, { "id": "bedrock/bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0", "slug": "bedrock-bedrock-us-gov-west-1-amazon-titan-text-premier-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "amazon.titan-text-premier-v1:0", "displayName": "amazon.titan-text-premier-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 42000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0000015, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Amazon Titan route id from official docs." } }, { "id": "bedrock/bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0", "slug": "bedrock-bedrock-us-gov-west-1-anthropic-claude-3-7-sonnet-20250219-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-7-sonnet-20250219-v1:0", "displayName": "anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.5999999999999996, "outputUsdPer1MTokens": 18, "cachedInputUsdPer1MTokens": 0.36, "cacheWriteUsdPer1MTokens": 4.5, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.5999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.0000045, "cache_read_input_token_cost": 3.6e-7, "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.0000045, "cache_read_input_token_cost": 3.6e-7, "input_cost_per_token": 0.0000036, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000018, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Anthropic route id from official docs." }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "slug": "bedrock-bedrock-us-gov-west-1-anthropic-claude-3-5-sonnet-20240620-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-5-sonnet-20240620-v1:0", "displayName": "anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.5999999999999996, "outputUsdPer1MTokens": 18, "cachedInputUsdPer1MTokens": 0.36, "cacheWriteUsdPer1MTokens": 4.5, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.5999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018, "cache_read_input_token_cost": 3.6e-7, "cache_creation_input_token_cost": 0.0000045 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000036, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000018, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3.6e-7, "cache_creation_input_token_cost": 0.0000045, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Anthropic route id from official docs." }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0", "slug": "bedrock-bedrock-us-gov-west-1-anthropic-claude-3-haiku-20240307-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-3-haiku-20240307-v1:0", "displayName": "anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": 0.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Anthropic route id from official docs." } }, { "id": "bedrock/bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock-bedrock-us-gov-west-1-anthropic-claude-sonnet-4-5-20250929-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000165, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/zh_cn/bedrock/latest/userguide/model-ids.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud Anthropic route id from official docs." }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock-bedrock-us-gov-west-1-claude-sonnet-4-5-20250929-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "claude-sonnet-4-5-20250929-v1:0", "displayName": "claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000165, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact gov-cloud alias from official docs." }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0", "slug": "bedrock-bedrock-us-gov-west-1-meta-llama3-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-70b-instruct-v1:0", "displayName": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.65, "outputUsdPer1MTokens": 3.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000265, "output_cost_per_token": 0.0000035 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 8000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "pdf_input": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000265, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.0000035, "supports_pdf_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0", "slug": "bedrock-bedrock-us-gov-west-1-meta-llama3-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-8b-instruct-v1:0", "displayName": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.65, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.00000265 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 8000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "pdf_input": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.00000265, "supports_pdf_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/us-west-1/meta.llama3-70b-instruct-v1:0", "slug": "bedrock-bedrock-us-west-1-meta-llama3-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-70b-instruct-v1:0", "displayName": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.65, "outputUsdPer1MTokens": 3.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000265, "output_cost_per_token": 0.0000035 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000265, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000035, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/us-west-1/meta.llama3-8b-instruct-v1:0", "slug": "bedrock-bedrock-us-west-1-meta-llama3-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-8b-instruct-v1:0", "displayName": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-us-west-2-1-month-commitment-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.011, "perSecondOutputUsd": 0.011, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.011, "output_cost_per_second": 0.011 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.011, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude Instant commitment variant from official docs" } }, { "id": "bedrock/bedrock/us-west-2/1-month-commitment/anthropic.claude-v1", "slug": "bedrock-bedrock-us-west-2-1-month-commitment-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0175, "perSecondOutputUsd": 0.0175, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0175, "output_cost_per_second": 0.0175 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.0175, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://aws-blogs-artifacts-public.s3.amazonaws.com/ML-15986/AmazonBedrock_UserGuide.pdf", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-claude.html" ], "manual_model_modalities_note": "Bedrock exact regional commitment alias from official docs." } }, { "id": "bedrock/bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1", "slug": "bedrock-bedrock-us-west-2-1-month-commitment-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0175, "perSecondOutputUsd": 0.0175, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0175, "output_cost_per_second": 0.0175 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.0175, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude 2.1 commitment variant from official docs" } }, { "id": "bedrock/bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-us-west-2-6-month-commitment-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00611, "perSecondOutputUsd": 0.00611, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00611, "output_cost_per_second": 0.00611 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.00611, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude Instant commitment variant from official docs" } }, { "id": "bedrock/bedrock/us-west-2/6-month-commitment/anthropic.claude-v1", "slug": "bedrock-bedrock-us-west-2-6-month-commitment-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00972, "perSecondOutputUsd": 0.00972, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00972, "output_cost_per_second": 0.00972 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.00972 } }, { "id": "bedrock/bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1", "slug": "bedrock-bedrock-us-west-2-6-month-commitment-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00972, "perSecondOutputUsd": 0.00972, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00972, "output_cost_per_second": 0.00972 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_second": 0.00972, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Anthropic Claude 2.1 commitment variant from official docs" } }, { "id": "bedrock/bedrock/us-west-2/anthropic.claude-instant-v1", "slug": "bedrock-bedrock-us-west-2-anthropic-claude-instant-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-instant-v1", "displayName": "anthropic.claude-instant-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/anthropic.claude-instant-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0000024, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact regional Anthropic route id from official docs." } }, { "id": "bedrock/bedrock/us-west-2/anthropic.claude-v1", "slug": "bedrock-bedrock-us-west-2-anthropic-claude-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v1", "displayName": "anthropic.claude-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/anthropic.claude-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_tool_choice": true } }, { "id": "bedrock/bedrock/us-west-2/anthropic.claude-v2:1", "slug": "bedrock-bedrock-us-west-2-anthropic-claude-v2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-v2:1", "displayName": "anthropic.claude-v2:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 100000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/anthropic.claude-v2:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact regional Anthropic Claude 2.1 route id from official docs." } }, { "id": "bedrock/bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2", "slug": "bedrock-bedrock-us-west-2-mistral-mistral-7b-instruct-v0-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mistral-7b-instruct-v0:2", "displayName": "mistral.mistral-7b-instruct-v0:2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "bedrock/bedrock/us-west-2/mistral.mistral-large-2402-v1:0", "slug": "bedrock-bedrock-us-west-2-mistral-mistral-large-2402-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mistral-large-2402-v1:0", "displayName": "mistral.mistral-large-2402-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/mistral.mistral-large-2402-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" } }, { "id": "bedrock/bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1", "slug": "bedrock-bedrock-us-west-2-mistral-mixtral-8x7b-instruct-v0-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mixtral-8x7b-instruct-v0:1", "displayName": "mistral.mixtral-8x7b-instruct-v0:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.44999999999999996, "outputUsdPer1MTokens": 0.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.44999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.5e-7, "output_cost_per_token": 7e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 7e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" } }, { "id": "bedrock/bedrock/us-west-2/deepseek.v3.2", "slug": "bedrock-bedrock-us-west-2-deepseek-v3-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "deepseek.v3.2", "displayName": "deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.62, "outputUsdPer1MTokens": 1.85, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.62, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/deepseek.v3.2", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000185, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" ], "manual_model_modalities_note": "Bedrock exact DeepSeek route id from official docs." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock/bedrock/us-west-2/minimax.minimax-m2.1", "slug": "bedrock-bedrock-us-west-2-minimax-minimax-m2-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs." }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock/bedrock/us-west-2/minimax.minimax-m2.5", "slug": "bedrock-bedrock-us-west-2-minimax-minimax-m2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock exact MiniMax route id from official docs." }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock/bedrock/us-west-2/moonshotai.kimi-k2-thinking", "slug": "bedrock-bedrock-us-west-2-moonshotai-kimi-k2-thinking", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2-thinking", "displayName": "moonshotai.kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/moonshotai.kimi-k2-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000025, "supports_function_calling": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs." } }, { "id": "bedrock/bedrock/us-west-2/moonshotai.kimi-k2.5", "slug": "bedrock-bedrock-us-west-2-moonshotai-kimi-k2-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "moonshotai.kimi-k2.5", "displayName": "moonshotai.kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/moonshotai.kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" ], "manual_model_modalities_note": "Bedrock exact Moonshot route id from official docs." }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "bedrock/bedrock/us-west-2/qwen.qwen3-coder-next", "slug": "bedrock-bedrock-us-west-2-qwen-qwen3-coder-next", "provider": "Bedrock", "providerSlug": "bedrock", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" ], "manual_model_modalities_note": "Bedrock exact Qwen route id from official docs." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock/bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0", "slug": "bedrock-bedrock-us-anthropic-claude-3-5-haiku-20241022-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.anthropic.claude-3-5-haiku-20241022-v1:0", "displayName": "us.anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": 0.08, "cacheWriteUsdPer1MTokens": 1, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000001, "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000001, "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 8e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000004, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-5-haiku.html", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/ru/api/claude-on-amazon-bedrock" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "aidercodeeditingleaderboard_score_claude35haiku20241022_benchmarkleaderboard_68": { "label": "Aider Code Editing", "category": "coding", "score": 75.2, "scoreText": "75.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Haiku", "exactModelOrSnapshot": "claude-3-5-haiku-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." } } }, { "id": "black_forest_labs/black_forest_labs/flux-kontext-pro", "slug": "black_forest_labs-black_forest_labs-flux-kontext-pro", "provider": "black_forest_labs", "providerSlug": "black_forest_labs", "name": "flux-kontext-pro", "displayName": "flux-kontext-pro", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "black_forest_labs/flux-kontext-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://bfl.ai/pricing" }, "rawLitellm": { "litellm_provider": "black_forest_labs", "mode": "image_edit", "output_cost_per_image": 0.04, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ] } }, { "id": "black_forest_labs/black_forest_labs/flux-kontext-max", "slug": "black_forest_labs-black_forest_labs-flux-kontext-max", "provider": "black_forest_labs", "providerSlug": "black_forest_labs", "name": "flux-kontext-max", "displayName": "flux-kontext-max", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 80000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.08 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "black_forest_labs/flux-kontext-max", "syncedAt": "2026-05-28", "sourceUrl": "https://bfl.ai/pricing" }, "rawLitellm": { "litellm_provider": "black_forest_labs", "mode": "image_edit", "output_cost_per_image": 0.08, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ] } }, { "id": "black_forest_labs/black_forest_labs/flux-pro-1.0-fill", "slug": "black_forest_labs-black_forest_labs-flux-pro-1-0-fill", "provider": "black_forest_labs", "providerSlug": "black_forest_labs", "name": "flux-pro-1.0-fill", "displayName": "flux-pro-1.0-fill", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 50000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.05 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "black_forest_labs/flux-pro-1.0-fill", "syncedAt": "2026-05-28", "sourceUrl": "https://bfl.ai/pricing" }, "rawLitellm": { "litellm_provider": "black_forest_labs", "mode": "image_edit", "output_cost_per_image": 0.05, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "black_forest_labs/black_forest_labs/flux-pro-1.0-expand", "slug": "black_forest_labs-black_forest_labs-flux-pro-1-0-expand", "provider": "black_forest_labs", "providerSlug": "black_forest_labs", "name": "flux-pro-1.0-expand", "displayName": "flux-pro-1.0-expand", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 50000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.05 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "black_forest_labs/flux-pro-1.0-expand", "syncedAt": "2026-05-28", "sourceUrl": "https://bfl.ai/pricing" }, "rawLitellm": { "litellm_provider": "black_forest_labs", "mode": "image_edit", "output_cost_per_image": 0.05, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "black_forest_labs/black_forest_labs/flux-pro-1.1", "slug": "black_forest_labs-black_forest_labs-flux-pro-1-1", "provider": "black_forest_labs", "providerSlug": "black_forest_labs", "name": "flux-pro-1.1", "displayName": "flux-pro-1.1", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "black_forest_labs/flux-pro-1.1", "syncedAt": "2026-05-28", "sourceUrl": "https://bfl.ai/pricing" }, "rawLitellm": { "litellm_provider": "black_forest_labs", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "black_forest_labs/black_forest_labs/flux-pro-1.1-ultra", "slug": "black_forest_labs-black_forest_labs-flux-pro-1-1-ultra", "provider": "black_forest_labs", "providerSlug": "black_forest_labs", "name": "flux-pro-1.1-ultra", "displayName": "flux-pro-1.1-ultra", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "black_forest_labs/flux-pro-1.1-ultra", "syncedAt": "2026-05-28", "sourceUrl": "https://bfl.ai/pricing" }, "rawLitellm": { "litellm_provider": "black_forest_labs", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "black_forest_labs/black_forest_labs/flux-dev", "slug": "black_forest_labs-black_forest_labs-flux-dev", "provider": "black_forest_labs", "providerSlug": "black_forest_labs", "name": "flux-dev", "displayName": "flux-dev", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 25000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.025 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "black_forest_labs/flux-dev", "syncedAt": "2026-05-28", "sourceUrl": "https://bfl.ai/pricing" }, "rawLitellm": { "litellm_provider": "black_forest_labs", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "black_forest_labs/black_forest_labs/flux-pro", "slug": "black_forest_labs-black_forest_labs-flux-pro", "provider": "black_forest_labs", "providerSlug": "black_forest_labs", "name": "flux-pro", "displayName": "flux-pro", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 50000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.05 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "black_forest_labs/flux-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://bfl.ai/pricing" }, "rawLitellm": { "litellm_provider": "black_forest_labs", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "cerebras/cerebras/llama-3.3-70b", "slug": "cerebras-cerebras-llama-3-3-70b", "provider": "cerebras", "providerSlug": "cerebras", "name": "llama-3.3-70b", "displayName": "llama-3.3-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.85, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.85, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8.5e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cerebras/llama-3.3-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8.5e-7, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "cerebras/cerebras/llama3.1-70b", "slug": "cerebras-cerebras-llama3-1-70b", "provider": "cerebras", "providerSlug": "cerebras", "name": "llama3.1-70b", "displayName": "llama3.1-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cerebras/llama3.1-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "cerebras/cerebras/llama3.1-8b", "slug": "cerebras-cerebras-llama3-1-8b", "provider": "cerebras", "providerSlug": "cerebras", "name": "llama3.1-8b", "displayName": "llama3.1-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cerebras/llama3.1-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "cerebras/cerebras/gpt-oss-120b", "slug": "cerebras-cerebras-gpt-oss-120b", "provider": "cerebras", "providerSlug": "cerebras", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 0.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 7.5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cerebras/gpt-oss-120b", "syncedAt": "2026-05-28", "sourceUrl": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras" }, "rawLitellm": { "input_cost_per_token": 3.5e-7, "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.5e-7, "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "cerebras/cerebras/qwen-3-32b", "slug": "cerebras-cerebras-qwen-3-32b", "provider": "cerebras", "providerSlug": "cerebras", "name": "qwen-3-32b", "displayName": "qwen-3-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cerebras/qwen-3-32b", "syncedAt": "2026-05-28", "sourceUrl": "https://inference-docs.cerebras.ai/support/pricing" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-7, "source": "https://inference-docs.cerebras.ai/support/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "cerebras/cerebras/zai-glm-4.6", "slug": "cerebras-cerebras-zai-glm-4-6", "provider": "cerebras", "providerSlug": "cerebras", "name": "zai-glm-4.6", "displayName": "zai-glm-4.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.25, "outputUsdPer1MTokens": 2.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000225, "output_cost_per_token": 0.00000275 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-01-20" }, "source": { "type": "litellm", "litellmKey": "cerebras/zai-glm-4.6", "syncedAt": "2026-05-28", "sourceUrl": "https://www.cerebras.ai/pricing" }, "rawLitellm": { "deprecation_date": "2026-01-20", "input_cost_per_token": 0.00000225, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000275, "source": "https://www.cerebras.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_zaiglm46_benchmarkleaderboard_282": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_zaiglm46_benchmarkleaderboard_283": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_zaiglm46_benchmarkleaderboard_284": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_zaiglm46_benchmarkleaderboard_285": { "label": "GPQA Diamond", "category": "reasoning", "score": 78, "scoreText": "78.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_artificialanalysisintelligenceindex_score_zaiglm46_benchmarkleaderboard_310": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysiscodingindex_score_zaiglm46_benchmarkleaderboard_311": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysisagenticindex_score_zaiglm46_benchmarkleaderboard_312": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." } } }, { "id": "cerebras/cerebras/zai-glm-4.7", "slug": "cerebras-cerebras-zai-glm-4-7", "provider": "cerebras", "providerSlug": "cerebras", "name": "zai-glm-4.7", "displayName": "zai-glm-4.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.25, "outputUsdPer1MTokens": 2.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000225, "output_cost_per_token": 0.00000275 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cerebras/zai-glm-4.7", "syncedAt": "2026-05-28", "sourceUrl": "https://www.cerebras.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 0.00000225, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000275, "source": "https://www.cerebras.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "nlp_cloud/chatdolphin", "slug": "nlp_cloud-chatdolphin", "provider": "nlp_cloud", "providerSlug": "nlp_cloud", "name": "chatdolphin", "displayName": "chatdolphin", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatdolphin", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-7 } }, { "id": "openai/chatgpt-4o-latest", "slug": "openai-chatgpt-4o-latest", "provider": "OpenAI", "providerSlug": "openai", "name": "chatgpt-4o-latest", "displayName": "chatgpt-4o-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2025-11-18", "shutdownDate": "2026-02-17", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "OpenAI deprecations page lists this snapshot with a fixed shutdown date." }, "source": { "type": "litellm", "litellmKey": "chatgpt-4o-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/chatgpt-4o-latest" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "OpenAI deprecations page lists this snapshot with a fixed shutdown date." } }, { "id": "openai/gpt-4o-transcribe-diarize", "slug": "openai-gpt-4o-transcribe-diarize", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-transcribe-diarize", "displayName": "gpt-4o-transcribe-diarize", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 2.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.0000025, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": null, "maxInputTokens": 16000, "maxOutputTokens": 2000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-transcribe-diarize", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.0000025, "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "anthropic/claude-haiku-4-5-20251001", "slug": "anthropic-claude-haiku-4-5-20251001", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-haiku-4-5-20251001", "displayName": "claude-haiku-4-5-20251001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": 1.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "computer_use": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": "2026-10-15", "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Anthropic lists 'Not sooner than October 15, 2026' rather than a fixed retirement date." }, "source": { "type": "litellm", "litellmKey": "claude-haiku-4-5-20251001", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000005, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Anthropic lists 'Not sooner than October 15, 2026' rather than a fixed retirement date." }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "anthropic/claude-haiku-4-5", "slug": "anthropic-claude-haiku-4-5", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-haiku-4-5", "displayName": "claude-haiku-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": 1.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "computer_use": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "claude-haiku-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000005, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "anthropic/claude-3-7-sonnet-20250219", "slug": "anthropic-claude-3-7-sonnet-20250219", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-3-7-sonnet-20250219", "displayName": "claude-3-7-sonnet-20250219", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-02-19", "status": "retired", "announcementDate": "2025-10-28", "shutdownDate": "2026-02-19", "earliestShutdownDate": null, "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "claude-3-7-sonnet-20250219", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "deprecation_date": "2026-02-19", "input_cost_per_token": 0.000003, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "anthropic/claude-3-haiku-20240307", "slug": "anthropic-claude-3-haiku-20240307", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-3-haiku-20240307", "displayName": "claude-3-haiku-20240307", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": 0.3, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 3e-7, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-02-19", "shutdownDate": "2026-04-20", "earliestShutdownDate": null, "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "claude-3-haiku-20240307", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 3e-7, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 2.5e-7, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 264, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "anthropic/claude-3-opus-20240229", "slug": "anthropic-claude-3-opus-20240229", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-3-opus-20240229", "displayName": "claude-3-opus-20240229", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-05-01", "status": "retired", "announcementDate": "2025-06-30", "shutdownDate": "2026-01-05", "earliestShutdownDate": null, "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "claude-3-opus-20240229", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 0.0000015, "deprecation_date": "2026-05-01", "input_cost_per_token": 0.000015, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000075, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 395, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "aiderrefactoringleaderboard_score_claude3opus20240229_benchmarkleaderboard_69": { "label": "Aider Refactoring", "category": "coding", "score": 72.3, "scoreText": "72.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/refactor.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3 Opus", "exactModelOrSnapshot": "claude-3-opus-20240229", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Refactoring leaderboard row; diff edit format." } } }, { "id": "anthropic/claude-4-opus-20250514", "slug": "anthropic-claude-4-opus-20250514", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-4-opus-20250514", "displayName": "claude-4-opus-20250514", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "claude-4-opus-20250514", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override" } }, { "id": "anthropic/claude-4-sonnet-20250514", "slug": "anthropic-claude-4-sonnet-20250514", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-4-sonnet-20250514", "displayName": "claude-4-sonnet-20250514", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost": 3e-7, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token": 0.000015, "output_cost_per_token_above_200k_tokens": 0.0000225 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "claude-4-sonnet-20250514", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost": 3e-7, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_above_200k_tokens": 0.0000225, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override" } }, { "id": "anthropic/claude-sonnet-4-5", "slug": "anthropic-claude-sonnet-4-5", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-sonnet-4-5", "displayName": "claude-sonnet-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "claude-sonnet-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "anthropic/claude-sonnet-4-5-20250929", "slug": "anthropic-claude-sonnet-4-5-20250929", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-sonnet-4-5-20250929", "displayName": "claude-sonnet-4-5-20250929", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": "2026-09-29", "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Anthropic lists 'Not sooner than September 29, 2026' rather than a fixed retirement date." }, "source": { "type": "litellm", "litellmKey": "claude-sonnet-4-5-20250929", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "tool_use_system_prompt_tokens": 346, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Anthropic lists 'Not sooner than September 29, 2026' rather than a fixed retirement date." }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "anthropic/claude-sonnet-4-6", "slug": "anthropic-claude-sonnet-4-6", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-sonnet-4-6", "displayName": "claude-sonnet-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "adaptive_thinking": true, "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "output_config": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": "2027-02-17", "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Anthropic lists 'Not sooner than February 17, 2027' rather than a fixed retirement date." }, "source": { "type": "litellm", "litellmKey": "claude-sonnet-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_output_config": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Anthropic lists 'Not sooner than February 17, 2027' rather than a fixed retirement date." }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock/claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock-claude-sonnet-4-5-20250929-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "claude-sonnet-4-5-20250929-v1:0", "displayName": "claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html" ], "manual_model_modalities_note": "Bedrock exact alias from official docs." }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "anthropic/claude-opus-4-1", "slug": "anthropic-claude-opus-4-1", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-opus-4-1", "displayName": "claude-opus-4-1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.00003, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "claude-opus-4-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.00003, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "anthropic/claude-opus-4-1-20250805", "slug": "anthropic-claude-opus-4-1-20250805", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-opus-4-1-20250805", "displayName": "claude-opus-4-1-20250805", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.00003, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-08-05", "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": "2026-08-05", "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Anthropic lists 'Not sooner than August 5, 2026' rather than a fixed retirement date." }, "source": { "type": "litellm", "litellmKey": "claude-opus-4-1-20250805", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.00003, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "deprecation_date": "2026-08-05", "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Anthropic lists 'Not sooner than August 5, 2026' rather than a fixed retirement date." }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "anthropic/claude-opus-4-20250514", "slug": "anthropic-claude-opus-4-20250514", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-opus-4-20250514", "displayName": "claude-opus-4-20250514", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.00003, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-05-14", "status": "deprecated", "announcementDate": "2026-04-14", "shutdownDate": "2026-06-15", "earliestShutdownDate": null, "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "claude-opus-4-20250514", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.00003, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "deprecation_date": "2026-05-14", "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "anthropic/claude-opus-4-5-20251101", "slug": "anthropic-claude-opus-4-5-20251101", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-opus-4-5-20251101", "displayName": "claude-opus-4-5-20251101", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "minimal_reasoning_effort": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": "2026-11-24", "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Anthropic lists 'Not sooner than November 24, 2026' rather than a fixed retirement date." }, "source": { "type": "litellm", "litellmKey": "claude-opus-4-5-20251101", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Anthropic lists 'Not sooner than November 24, 2026' rather than a fixed retirement date." }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "anthropic/claude-opus-4-5", "slug": "anthropic-claude-opus-4-5", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-opus-4-5", "displayName": "claude-opus-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "minimal_reasoning_effort": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "claude-opus-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "anthropic/claude-opus-4-6", "slug": "anthropic-claude-opus-4-6", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-opus-4-6", "displayName": "claude-opus-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "adaptive_thinking": true, "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "output_config": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": "2027-02-05", "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Anthropic lists 'Not sooner than February 5, 2027' rather than a fixed retirement date." }, "source": { "type": "litellm", "litellmKey": "claude-opus-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "provider_specific_entry": { "us": 1.1, "fast": 6 }, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Anthropic lists 'Not sooner than February 5, 2027' rather than a fixed retirement date." }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "anthropic/claude-opus-4-6-20260205", "slug": "anthropic-claude-opus-4-6-20260205", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-opus-4-6-20260205", "displayName": "claude-opus-4-6-20260205", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "adaptive_thinking": true, "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true, "output_config": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "claude-opus-4-6-20260205", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "provider_specific_entry": { "us": 1.1, "fast": 6 }, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "supports_output_config": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "anthropic/claude-opus-4-7", "slug": "anthropic-claude-opus-4-7", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-opus-4-7", "displayName": "claude-opus-4-7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": true }, "raw": { "adaptive_thinking": true, "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true, "output_config": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": "2027-04-16", "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Anthropic lists 'Not sooner than April 16, 2027' rather than a fixed retirement date." }, "source": { "type": "litellm", "litellmKey": "claude-opus-4-7", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "provider_specific_entry": { "us": 1.1, "fast": 6 }, "supports_minimal_reasoning_effort": true, "supports_output_config": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Anthropic lists 'Not sooner than April 16, 2027' rather than a fixed retirement date." }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "anthropic/claude-opus-4-7-20260416", "slug": "anthropic-claude-opus-4-7-20260416", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-opus-4-7-20260416", "displayName": "claude-opus-4-7-20260416", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": true }, "raw": { "adaptive_thinking": true, "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true, "output_config": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "claude-opus-4-7-20260416", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "provider_specific_entry": { "us": 1.1, "fast": 6 }, "supports_minimal_reasoning_effort": true, "supports_output_config": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "anthropic/claude-sonnet-4-20250514", "slug": "anthropic-claude-sonnet-4-20250514", "provider": "Anthropic", "providerSlug": "anthropic", "name": "claude-sonnet-4-20250514", "displayName": "Claude Sonnet 4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-05-14", "status": "deprecated", "announcementDate": "2026-04-14", "shutdownDate": "2026-06-15", "earliestShutdownDate": null, "sourceUrls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "claude-sonnet-4-20250514", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-05-14", "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.claude.com/docs/en/about-claude/models/overview", "https://platform.claude.com/docs/en/build-with-claude/vision" ], "manual_model_modalities_note": "Anthropic Claude family exact-model override", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://platform.claude.com/docs/en/about-claude/model-deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "aider_polyglot": { "label": "Aider Polyglot", "category": "coding", "score": null, "metric": "percent_correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-23" }, "livebench": { "label": "LiveBench", "category": "general", "score": null, "metric": "overall", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-23" } } }, { "id": "cloudflare/cloudflare/@cf/meta/llama-2-7b-chat-fp16", "slug": "cloudflare-cloudflare-cf-meta-llama-2-7b-chat-fp16", "provider": "cloudflare", "providerSlug": "cloudflare", "name": "llama-2-7b-chat-fp16", "displayName": "llama-2-7b-chat-fp16", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.923, "outputUsdPer1MTokens": 1.923, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.923, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001923, "output_cost_per_token": 0.000001923 } }, "limits": { "contextWindow": 3072, "maxInputTokens": 3072, "maxOutputTokens": 3072, "maxTokens": 3072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-30", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.cloudflare.com/workers-ai/models/llama-2-7b-chat-fp16/" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Cloudflare model page labels this as Planned Deprecation." }, "source": { "type": "litellm", "litellmKey": "cloudflare/@cf/meta/llama-2-7b-chat-fp16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001923, "litellm_provider": "cloudflare", "max_input_tokens": 3072, "max_output_tokens": 3072, "max_tokens": 3072, "mode": "chat", "output_cost_per_token": 0.000001923, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.cloudflare.com/workers-ai/models/llama-2-7b-chat-fp16/" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Cloudflare model page labels this as Planned Deprecation." } }, { "id": "cloudflare/cloudflare/@cf/meta/llama-2-7b-chat-int8", "slug": "cloudflare-cloudflare-cf-meta-llama-2-7b-chat-int8", "provider": "cloudflare", "providerSlug": "cloudflare", "name": "llama-2-7b-chat-int8", "displayName": "llama-2-7b-chat-int8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.923, "outputUsdPer1MTokens": 1.923, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.923, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001923, "output_cost_per_token": 0.000001923 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-30", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.cloudflare.com/workers-ai/models/llama-2-7b-chat-int8/" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Cloudflare model page labels this as Planned Deprecation." }, "source": { "type": "litellm", "litellmKey": "cloudflare/@cf/meta/llama-2-7b-chat-int8", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001923, "litellm_provider": "cloudflare", "max_input_tokens": 2048, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.000001923, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.cloudflare.com/workers-ai/models/llama-2-7b-chat-int8/" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Cloudflare model page labels this as Planned Deprecation." } }, { "id": "cloudflare/cloudflare/@cf/mistral/mistral-7b-instruct-v0.1", "slug": "cloudflare-cloudflare-cf-mistral-mistral-7b-instruct-v0-1", "provider": "cloudflare", "providerSlug": "cloudflare", "name": "mistral-7b-instruct-v0.1", "displayName": "mistral-7b-instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.923, "outputUsdPer1MTokens": 1.923, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.923, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001923, "output_cost_per_token": 0.000001923 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-30", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.cloudflare.com/ai/models/%40cf/mistral/mistral-7b-instruct-v0.1/" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Cloudflare model page labels this as Planned Deprecation." }, "source": { "type": "litellm", "litellmKey": "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001923, "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000001923, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.cloudflare.com/ai/models/%40cf/mistral/mistral-7b-instruct-v0.1/" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Cloudflare model page labels this as Planned Deprecation." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "cloudflare/cloudflare/@hf/thebloke/codellama-7b-instruct-awq", "slug": "cloudflare-cloudflare-hf-thebloke-codellama-7b-instruct-awq", "provider": "cloudflare", "providerSlug": "cloudflare", "name": "codellama-7b-instruct-awq", "displayName": "codellama-7b-instruct-awq", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.923, "outputUsdPer1MTokens": 1.923, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.923, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001923, "output_cost_per_token": 0.000001923 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cloudflare/@hf/thebloke/codellama-7b-instruct-awq", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001923, "litellm_provider": "cloudflare", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000001923 }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "codestral/codestral/codestral-2405", "slug": "codestral-codestral-codestral-2405", "provider": "codestral", "providerSlug": "codestral", "name": "codestral-2405", "displayName": "codestral-2405", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "codestral/codestral-2405", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.mistral.ai/capabilities/code_generation/" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0, "source": "https://docs.mistral.ai/capabilities/code_generation/", "supports_assistant_prefill": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "codestral/codestral/codestral-latest", "slug": "codestral-codestral-codestral-latest", "provider": "codestral", "providerSlug": "codestral", "name": "codestral-latest", "displayName": "codestral-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "codestral/codestral-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.mistral.ai/capabilities/code_generation/" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0, "source": "https://docs.mistral.ai/capabilities/code_generation/", "supports_assistant_prefill": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "openai/codex-mini-latest", "slug": "openai-codex-mini-latest", "provider": "OpenAI", "providerSlug": "openai", "name": "codex-mini-latest", "displayName": "codex-mini-latest", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": 0.375, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3.75e-7, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2025-11-17", "shutdownDate": "2026-02-12", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "OpenAI deprecations page lists this snapshot with a fixed shutdown date." }, "source": { "type": "litellm", "litellmKey": "codex-mini-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 3.75e-7, "input_cost_per_token": 0.0000015, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.000006, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "OpenAI deprecations page lists this snapshot with a fixed shutdown date." } }, { "id": "bedrock/cohere.command-light-text-v14", "slug": "bedrock-cohere-command-light-text-v14", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.command-light-text-v14", "displayName": "cohere.command-light-text-v14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cohere.command-light-text-v14", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Cohere route id from official docs." } }, { "id": "bedrock/cohere.command-r-plus-v1:0", "slug": "bedrock-cohere-command-r-plus-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.command-r-plus-v1:0", "displayName": "cohere.command-r-plus-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cohere.command-r-plus-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-command-r-plus.html" ], "manual_model_modalities_note": "Bedrock exact Cohere route id from official docs." } }, { "id": "bedrock/cohere.command-r-v1:0", "slug": "bedrock-cohere-command-r-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.command-r-v1:0", "displayName": "cohere.command-r-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cohere.command-r-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-command-r.html" ], "manual_model_modalities_note": "Bedrock exact Cohere route id from official docs." } }, { "id": "bedrock/cohere.command-text-v14", "slug": "bedrock-cohere-command-text-v14", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.command-text-v14", "displayName": "cohere.command-text-v14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cohere.command-text-v14", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000015, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000002, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-cohere-command.html", "https://docs.aws.amazon.com/es_es/bedrock/latest/userguide/model-ids.html" ], "manual_model_modalities_note": "Bedrock exact Cohere route id from official docs." } }, { "id": "bedrock/cohere.embed-english-v3", "slug": "bedrock-cohere-embed-english-v3", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.embed-english-v3", "displayName": "cohere.embed-english-v3", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cohere.embed-english-v3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "bedrock", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "supports_embedding_image_input": true } }, { "id": "bedrock/cohere.embed-multilingual-v3", "slug": "bedrock-cohere-embed-multilingual-v3", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.embed-multilingual-v3", "displayName": "cohere.embed-multilingual-v3", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cohere.embed-multilingual-v3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "bedrock", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "supports_embedding_image_input": true } }, { "id": "bedrock/cohere.embed-v4:0", "slug": "bedrock-cohere-embed-v4-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.embed-v4:0", "displayName": "cohere.embed-v4:0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1536, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cohere.embed-v4:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1536, "supports_embedding_image_input": true } }, { "id": "cohere/cohere/embed-v4.0", "slug": "cohere-cohere-embed-v4-0", "provider": "Cohere", "providerSlug": "cohere", "name": "embed-v4.0", "displayName": "embed-v4.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1536, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cohere/embed-v4.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "cohere", "max_input_tokens": 128000, "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1536, "supports_embedding_image_input": true } }, { "id": "bedrock/cohere.rerank-v3-5:0", "slug": "bedrock-cohere-rerank-v3-5-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "cohere.rerank-v3-5:0", "displayName": "cohere.rerank-v3-5:0", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 32000, "maxDocumentChunksPerQuery": 100, "maxTokensPerDocumentChunk": 512 }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "cohere.rerank-v3-5:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "litellm_provider": "bedrock", "max_document_chunks_per_query": 100, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_query_tokens": 32000, "max_tokens": 32000, "max_tokens_per_document_chunk": 512, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "cohere/command", "slug": "cohere-command", "provider": "Cohere", "providerSlug": "cohere", "name": "command", "displayName": "command", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2025-09-15", "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://docs.cohere.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Cohere marks this model deprecated but does not assign a shutdown date yet." }, "source": { "type": "litellm", "litellmKey": "command", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.000002, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.cohere.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Cohere marks this model deprecated but does not assign a shutdown date yet." } }, { "id": "cohere_chat/command-a-03-2025", "slug": "cohere_chat-command-a-03-2025", "provider": "cohere_chat", "providerSlug": "cohere_chat", "name": "command-a-03-2025", "displayName": "command-a-03-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 256000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "command-a-03-2025", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "cohere_chat", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_accuracy_commanda_paper_130": { "label": "MMLU", "category": "general_knowledge", "score": 85.5, "scoreText": "85.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "mmlupro_accuracy_commanda_paper_131": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "gpqa_accuracy_commanda_paper_132": { "label": "GPQA", "category": "general_knowledge", "score": 50.8, "scoreText": "50.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "ifeval_strictaccuracy_commanda_paper_133": { "label": "IFEval", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "strict accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; instruction-following benchmark for Command A." }, "bfcloverall_score_commanda_paper_134": { "label": "BFCL", "category": "agentic", "score": 63.8, "scoreText": "63.8", "metric": "score", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 5 in the official technical report; BFCL values are taken from the official leaderboard." }, "taubenchretail_pass1_commanda_paper_135": { "label": "Taubench Retail", "category": "agentic", "score": 60, "scoreText": "P@1 60.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." }, "taubenchairline_pass1_commanda_paper_136": { "label": "Taubench Airline", "category": "agentic", "score": 45.3, "scoreText": "P@1 45.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." } } }, { "id": "cohere_chat/command-light", "slug": "cohere_chat-command-light", "provider": "cohere_chat", "providerSlug": "cohere_chat", "name": "command-light", "displayName": "command-light", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2025-09-15", "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://docs.cohere.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Cohere marks this model deprecated but does not assign a shutdown date yet." }, "source": { "type": "litellm", "litellmKey": "command-light", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "cohere_chat", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-7, "supports_tool_choice": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.cohere.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Cohere marks this model deprecated but does not assign a shutdown date yet." } }, { "id": "cohere/command-nightly", "slug": "cohere-command-nightly", "provider": "Cohere", "providerSlug": "cohere", "name": "command-nightly", "displayName": "command-nightly", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "command-nightly", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.000002 } }, { "id": "cohere_chat/command-r", "slug": "cohere_chat-command-r", "provider": "cohere_chat", "providerSlug": "cohere_chat", "name": "command-r", "displayName": "command-r", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2025-09-15", "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://docs.cohere.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Cohere deprecates the alias command-r and recommends command-r-08-2024 or newer." }, "source": { "type": "litellm", "litellmKey": "command-r", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.cohere.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Cohere deprecates the alias command-r and recommends command-r-08-2024 or newer." } }, { "id": "cohere_chat/command-r-08-2024", "slug": "cohere_chat-command-r-08-2024", "provider": "cohere_chat", "providerSlug": "cohere_chat", "name": "command-r-08-2024", "displayName": "command-r-08-2024", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "command-r-08-2024", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "cohere_chat/command-r-plus", "slug": "cohere_chat-command-r-plus", "provider": "cohere_chat", "providerSlug": "cohere_chat", "name": "command-r-plus", "displayName": "command-r-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2025-09-15", "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://docs.cohere.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Cohere deprecates the alias command-r-plus and recommends command-r-plus-08-2024 or newer." }, "source": { "type": "litellm", "litellmKey": "command-r-plus", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.cohere.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Cohere deprecates the alias command-r-plus and recommends command-r-plus-08-2024 or newer." } }, { "id": "cohere_chat/command-r-plus-08-2024", "slug": "cohere_chat-command-r-plus-08-2024", "provider": "cohere_chat", "providerSlug": "cohere_chat", "name": "command-r-plus-08-2024", "displayName": "command-r-plus-08-2024", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "command-r-plus-08-2024", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "cohere_chat/command-r7b-12-2024", "slug": "cohere_chat-command-r7b-12-2024", "provider": "cohere_chat", "providerSlug": "cohere_chat", "name": "command-r7b-12-2024", "displayName": "command-r7b-12-2024", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.0375, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 3.75e-8 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "command-r7b-12-2024", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.cohere.com/v2/docs/command-r7b" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.75e-8, "source": "https://docs.cohere.com/v2/docs/command-r7b", "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_accuracy_commandr7b_paper_137": { "label": "MMLU", "category": "general_knowledge", "score": 65.2, "scoreText": "65.2", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-r7b", "exactModelOrSnapshot": "Command R7B", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command R7B." }, "gpqa_accuracy_commandr7b_paper_138": { "label": "GPQA", "category": "general_knowledge", "score": 26.3, "scoreText": "26.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-r7b", "exactModelOrSnapshot": "Command R7B", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command R7B." }, "bfcloverall_score_commandr7b_paper_139": { "label": "BFCL", "category": "agentic", "score": 52.2, "scoreText": "52.2", "metric": "score", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-r7b", "exactModelOrSnapshot": "Command R7B", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 5 in the official technical report; BFCL values are taken from the official leaderboard." } } }, { "id": "azure/computer-use-preview", "slug": "azure-computer-use-preview", "provider": "Azure", "providerSlug": "azure", "name": "computer-use-preview", "displayName": "computer-use-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000012 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 8192, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "computer-use-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 0.000012, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "openai/dall-e-2", "slug": "openai-dall-e-2", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-2", "displayName": "dall-e-2", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 20000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.02 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits", "/v1/images/variations" ], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2025-11-14", "shutdownDate": "2026-05-12", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Docs list the base model id. Local resolution-specific variants are not overridden here." }, "source": { "type": "litellm", "litellmKey": "dall-e-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.02, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits", "/v1/images/variations" ], "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Docs list the base model id. Local resolution-specific variants are not overridden here." } }, { "id": "openai/dall-e-3", "slug": "openai-dall-e-3", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-3", "displayName": "dall-e-3", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 40000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2025-11-14", "shutdownDate": "2026-05-12", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.04, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ], "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "deepseek/deepseek-chat", "slug": "deepseek-deepseek-chat", "provider": "DeepSeek", "providerSlug": "deepseek", "name": "deepseek-chat", "displayName": "DeepSeek Chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.28, "outputUsdPer1MTokens": 0.42, "cachedInputUsdPer1MTokens": 0.028, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.28, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4.2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-24", "shutdownDate": "2026-07-24", "earliestShutdownDate": null, "sourceUrls": [ "https://api-docs.deepseek.com/updates/" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "DeepSeek changelog says the legacy API model name deepseek-chat will be discontinued on 2026-07-24." }, "source": { "type": "litellm", "litellmKey": "deepseek-chat", "syncedAt": "2026-05-28", "sourceUrl": "https://api-docs.deepseek.com/quick_start/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.8e-7, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-7, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://api-docs.deepseek.com/updates/" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "DeepSeek changelog says the legacy API model name deepseek-chat will be discontinued on 2026-07-24." } }, { "id": "deepseek/deepseek-reasoner", "slug": "deepseek-deepseek-reasoner", "provider": "DeepSeek", "providerSlug": "deepseek", "name": "deepseek-reasoner", "displayName": "deepseek-reasoner", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.28, "outputUsdPer1MTokens": 0.42, "cachedInputUsdPer1MTokens": 0.028, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.28, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4.2e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 131072, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "native_streaming": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-24", "shutdownDate": "2026-07-24", "earliestShutdownDate": null, "sourceUrls": [ "https://api-docs.deepseek.com/updates/" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "DeepSeek changelog says the legacy API model name deepseek-reasoner will be discontinued on 2026-07-24." }, "source": { "type": "litellm", "litellmKey": "deepseek-reasoner", "syncedAt": "2026-05-28", "sourceUrl": "https://api-docs.deepseek.com/quick_start/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.8e-7, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-7, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://api-docs.deepseek.com/updates/" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "DeepSeek changelog says the legacy API model name deepseek-reasoner will be discontinued on 2026-07-24." } }, { "id": "dashscope/dashscope/qwen-coder", "slug": "dashscope-dashscope-qwen-coder", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-coder", "displayName": "qwen-coder", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 1000000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-coder", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen-flash", "slug": "dashscope-dashscope-qwen-flash", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-flash", "displayName": "qwen-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 32768, "maxInputTokens": 997952, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "range": [ 0, 256000 ] }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "range": [ 256000, 1000000 ] } ] } }, { "id": "dashscope/dashscope/qwen-flash-2025-07-28", "slug": "dashscope-dashscope-qwen-flash-2025-07-28", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-flash-2025-07-28", "displayName": "qwen-flash-2025-07-28", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 32768, "maxInputTokens": 997952, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-flash-2025-07-28", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "range": [ 0, 256000 ] }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "range": [ 256000, 1000000 ] } ] } }, { "id": "dashscope/dashscope/qwen-max", "slug": "dashscope-dashscope-qwen-max", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-max", "displayName": "qwen-max", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.5999999999999999, "outputUsdPer1MTokens": 6.3999999999999995, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000064 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 30720, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-max", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 0.0000016, "litellm_provider": "dashscope", "max_input_tokens": 30720, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000064, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen-plus", "slug": "dashscope-dashscope-qwen-plus", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-plus", "displayName": "qwen-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 129024, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-plus", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen-plus-2025-01-25", "slug": "dashscope-dashscope-qwen-plus-2025-01-25", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-plus-2025-01-25", "displayName": "qwen-plus-2025-01-25", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 129024, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-plus-2025-01-25", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen-plus-2025-04-28", "slug": "dashscope-dashscope-qwen-plus-2025-04-28", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-plus-2025-04-28", "displayName": "qwen-plus-2025-04-28", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 4, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 129024, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-plus-2025-04-28", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen-plus-2025-07-14", "slug": "dashscope-dashscope-qwen-plus-2025-07-14", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-plus-2025-07-14", "displayName": "qwen-plus-2025-07-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 4, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 129024, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-plus-2025-07-14", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen-plus-2025-07-28", "slug": "dashscope-dashscope-qwen-plus-2025-07-28", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-plus-2025-07-28", "displayName": "qwen-plus-2025-07-28", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 32768, "maxInputTokens": 997952, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-plus-2025-07-28", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ] } }, { "id": "dashscope/dashscope/qwen-plus-2025-09-11", "slug": "dashscope-dashscope-qwen-plus-2025-09-11", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-plus-2025-09-11", "displayName": "qwen-plus-2025-09-11", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 32768, "maxInputTokens": 997952, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-plus-2025-09-11", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ] } }, { "id": "dashscope/dashscope/qwen-plus-latest", "slug": "dashscope-dashscope-qwen-plus-latest", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-plus-latest", "displayName": "qwen-plus-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 32768, "maxInputTokens": 997952, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-plus-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ] } }, { "id": "dashscope/dashscope/qwen-turbo", "slug": "dashscope-dashscope-qwen-turbo", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-turbo", "displayName": "qwen-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.5, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_reasoning_token": 5e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 129024, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-turbo", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-7, "output_cost_per_token": 2e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen-turbo-2024-11-01", "slug": "dashscope-dashscope-qwen-turbo-2024-11-01", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-turbo-2024-11-01", "displayName": "qwen-turbo-2024-11-01", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-turbo-2024-11-01", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen-turbo-2025-04-28", "slug": "dashscope-dashscope-qwen-turbo-2025-04-28", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-turbo-2025-04-28", "displayName": "qwen-turbo-2025-04-28", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.5, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_reasoning_token": 5e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 1000000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-turbo-2025-04-28", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-7, "output_cost_per_token": 2e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen-turbo-latest", "slug": "dashscope-dashscope-qwen-turbo-latest", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-turbo-latest", "displayName": "qwen-turbo-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.5, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_reasoning_token": 5e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 1000000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-turbo-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-7, "output_cost_per_token": 2e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen3-30b-a3b", "slug": "dashscope-dashscope-qwen3-30b-a3b", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-30b-a3b", "displayName": "qwen3-30b-a3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16384, "maxInputTokens": 129024, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-30b-a3b", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen3-coder-flash", "slug": "dashscope-dashscope-qwen3-coder-flash", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-coder-flash", "displayName": "qwen3-coder-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 65536, "maxInputTokens": 997952, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-coder-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "range": [ 0, 32000 ] }, { "cache_read_input_token_cost": 1.2e-7, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000025, "range": [ 32000, 128000 ] }, { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004, "range": [ 128000, 256000 ] }, { "cache_read_input_token_cost": 4e-7, "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000096, "range": [ 256000, 1000000 ] } ] }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "dashscope/dashscope/qwen3-coder-flash-2025-07-28", "slug": "dashscope-dashscope-qwen3-coder-flash-2025-07-28", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-coder-flash-2025-07-28", "displayName": "qwen3-coder-flash-2025-07-28", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 65536, "maxInputTokens": 997952, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-coder-flash-2025-07-28", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "range": [ 0, 32000 ] }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000025, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004, "range": [ 128000, 256000 ] }, { "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000096, "range": [ 256000, 1000000 ] } ] }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "dashscope/dashscope/qwen3-coder-plus", "slug": "dashscope-dashscope-qwen3-coder-plus", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-coder-plus", "displayName": "qwen3-coder-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 65536, "maxInputTokens": 997952, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-coder-plus", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "range": [ 0, 32000 ] }, { "cache_read_input_token_cost": 1.8e-7, "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.000009, "range": [ 32000, 128000 ] }, { "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 256000 ] }, { "cache_read_input_token_cost": 6e-7, "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00006, "range": [ 256000, 1000000 ] } ] }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "dashscope/dashscope/qwen3-coder-plus-2025-07-22", "slug": "dashscope-dashscope-qwen3-coder-plus-2025-07-22", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-coder-plus-2025-07-22", "displayName": "qwen3-coder-plus-2025-07-22", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 65536, "maxInputTokens": 997952, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-coder-plus-2025-07-22", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.000009, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 256000 ] }, { "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00006, "range": [ 256000, 1000000 ] } ] }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "dashscope/dashscope/qwen3-max-preview", "slug": "dashscope-dashscope-qwen3-max-preview", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-max-preview", "displayName": "qwen3-max-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 65536, "maxInputTokens": 258048, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-max-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ] }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_qwenqwen3max_benchmarkleaderboard_279": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 31.3, "scoreText": "31.3", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_qwenqwen3max_benchmarkleaderboard_280": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 26.4, "scoreText": "26.4", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_qwenqwen3max_benchmarkleaderboard_281": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 43, "scoreText": "43.0", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "dashscope/dashscope/qwen3-max", "slug": "dashscope-dashscope-qwen3-max", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-max", "displayName": "qwen3-max", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 65536, "maxInputTokens": 258048, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-max", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ] }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_qwenqwen3max_benchmarkleaderboard_279": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 31.3, "scoreText": "31.3", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_qwenqwen3max_benchmarkleaderboard_280": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 26.4, "scoreText": "26.4", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_qwenqwen3max_benchmarkleaderboard_281": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 43, "scoreText": "43.0", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "dashscope/dashscope/qwen3-max-2026-01-23", "slug": "dashscope-dashscope-qwen3-max-2026-01-23", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-max-2026-01-23", "displayName": "qwen3-max-2026-01-23", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 65536, "maxInputTokens": 258048, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-max-2026-01-23", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ] }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_qwenqwen3max_benchmarkleaderboard_279": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 31.3, "scoreText": "31.3", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_qwenqwen3max_benchmarkleaderboard_280": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 26.4, "scoreText": "26.4", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_qwenqwen3max_benchmarkleaderboard_281": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 43, "scoreText": "43.0", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "dashscope/dashscope/qwen3-next-80b-a3b-instruct", "slug": "dashscope-dashscope-qwen3-next-80b-a3b-instruct", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-next-80b-a3b-instruct", "displayName": "qwen3-next-80b-a3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262144, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-next-80b-a3b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "dashscope/dashscope/qwen3-next-80b-a3b-thinking", "slug": "dashscope-dashscope-qwen3-next-80b-a3b-thinking", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-next-80b-a3b-thinking", "displayName": "qwen3-next-80b-a3b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262144, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-next-80b-a3b-thinking", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "dashscope/dashscope/qwen3-vl-235b-a22b-instruct", "slug": "dashscope-dashscope-qwen3-vl-235b-a22b-instruct", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-vl-235b-a22b-instruct", "displayName": "qwen3-vl-235b-a22b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-vl-235b-a22b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000016, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "dashscope/dashscope/qwen3-vl-235b-a22b-thinking", "slug": "dashscope-dashscope-qwen3-vl-235b-a22b-thinking", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-vl-235b-a22b-thinking", "displayName": "qwen3-vl-235b-a22b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-vl-235b-a22b-thinking", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000004, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "dashscope/dashscope/qwen3-vl-32b-instruct", "slug": "dashscope-dashscope-qwen3-vl-32b-instruct", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-vl-32b-instruct", "displayName": "qwen3-vl-32b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.16, "outputUsdPer1MTokens": 0.64, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.16, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.6e-7, "output_cost_per_token": 6.4e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-vl-32b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" }, "rawLitellm": { "input_cost_per_token": 1.6e-7, "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "dashscope/dashscope/qwen3-vl-32b-thinking", "slug": "dashscope-dashscope-qwen3-vl-32b-thinking", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-vl-32b-thinking", "displayName": "qwen3-vl-32b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.16, "outputUsdPer1MTokens": 2.87, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.16, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.6e-7, "output_cost_per_token": 0.00000287 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-vl-32b-thinking", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" }, "rawLitellm": { "input_cost_per_token": 1.6e-7, "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.00000287, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "dashscope/dashscope/qwen3-vl-plus", "slug": "dashscope-dashscope-qwen3-vl-plus", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3-vl-plus", "displayName": "qwen3-vl-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 32768, "maxInputTokens": 260096, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3-vl-plus", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 260096, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000016, "range": [ 0, 32000 ] }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000048, "range": [ 128000, 256000 ] } ] } }, { "id": "dashscope/dashscope/qwen3.5-plus", "slug": "dashscope-dashscope-qwen3-5-plus", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen3.5-plus", "displayName": "qwen3.5-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 65536, "maxInputTokens": 991808, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen3.5-plus", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000024, "range": [ 0, 256000 ] }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "range": [ 256000, 1000000 ] } ] } }, { "id": "dashscope/dashscope/qwq-plus", "slug": "dashscope-dashscope-qwq-plus", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwq-plus", "displayName": "qwq-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 98304, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwq-plus", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "dashscope", "max_input_tokens": 98304, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000024, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "dashscope/dashscope/qwen-image-2.0", "slug": "dashscope-dashscope-qwen-image-2-0", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-image-2.0", "displayName": "qwen-image-2.0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-image-2.0", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "mode": "image_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "dashscope/dashscope/qwen-image-2.0-pro", "slug": "dashscope-dashscope-qwen-image-2-0-pro", "provider": "dashscope", "providerSlug": "dashscope", "name": "qwen-image-2.0-pro", "displayName": "qwen-image-2.0-pro", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dashscope/qwen-image-2.0-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/models" }, "rawLitellm": { "litellm_provider": "dashscope", "mode": "image_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "databricks/databricks/databricks-bge-large-en", "slug": "databricks-databricks-databricks-bge-large-en", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-bge-large-en", "displayName": "databricks-bge-large-en", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.10003000000000001, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.10003000000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.0003e-7, "input_dbu_cost_per_token": 0.000001429, "output_cost_per_token": 0, "output_dbu_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-bge-large-en", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 1.0003e-7, "input_dbu_cost_per_token": 0.000001429, "litellm_provider": "databricks", "max_input_tokens": 512, "max_tokens": 512, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "embedding", "output_cost_per_token": 0, "output_dbu_cost_per_token": 0, "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "benchmarks": { "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "databricks/databricks/databricks-claude-3-7-sonnet", "slug": "databricks-databricks-databricks-claude-3-7-sonnet", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-claude-3-7-sonnet", "displayName": "databricks-claude-3-7-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.9999900000000004, "outputUsdPer1MTokens": 15.000020000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.9999900000000004, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000029999900000000002, "input_dbu_cost_per_token": 0.000042857, "output_cost_per_token": 0.000015000020000000002, "output_dbu_cost_per_token": 0.000214286 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-claude-3-7-sonnet", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.0000029999900000000002, "input_dbu_cost_per_token": 0.000042857, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.000015000020000000002, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "databricks/databricks/databricks-claude-haiku-4-5", "slug": "databricks-databricks-databricks-claude-haiku-4-5", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-claude-haiku-4-5", "displayName": "databricks-claude-haiku-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.0000200000000001, "outputUsdPer1MTokens": 5.00003, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.0000200000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000100002, "input_dbu_cost_per_token": 0.000014286, "output_cost_per_token": 0.00000500003, "output_dbu_cost_per_token": 0.000071429 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-claude-haiku-4-5", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.00000100002, "input_dbu_cost_per_token": 0.000014286, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.00000500003, "output_dbu_cost_per_token": 0.000071429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "databricks/databricks/databricks-claude-opus-4", "slug": "databricks-databricks-databricks-claude-opus-4", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-claude-opus-4", "displayName": "databricks-claude-opus-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15.000020000000001, "outputUsdPer1MTokens": 75.00003000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15.000020000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015000020000000002, "input_dbu_cost_per_token": 0.000214286, "output_cost_per_token": 0.00007500003000000001, "output_dbu_cost_per_token": 0.001071429 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-claude-opus-4", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.000015000020000000002, "input_dbu_cost_per_token": 0.000214286, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.00007500003000000001, "output_dbu_cost_per_token": 0.001071429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "databricks/databricks/databricks-claude-opus-4-1", "slug": "databricks-databricks-databricks-claude-opus-4-1", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-claude-opus-4-1", "displayName": "databricks-claude-opus-4-1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15.000020000000001, "outputUsdPer1MTokens": 75.00003000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15.000020000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015000020000000002, "input_dbu_cost_per_token": 0.000214286, "output_cost_per_token": 0.00007500003000000001, "output_dbu_cost_per_token": 0.001071429 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-claude-opus-4-1", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.000015000020000000002, "input_dbu_cost_per_token": 0.000214286, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.00007500003000000001, "output_dbu_cost_per_token": 0.001071429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "databricks/databricks/databricks-claude-opus-4-5", "slug": "databricks-databricks-databricks-claude-opus-4-5", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-claude-opus-4-5", "displayName": "databricks-claude-opus-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.00003, "outputUsdPer1MTokens": 25.000010000000003, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.00003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000500003, "input_dbu_cost_per_token": 0.000071429, "output_cost_per_token": 0.000025000010000000002, "output_dbu_cost_per_token": 0.000357143 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "minimal_reasoning_effort": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-claude-opus-4-5", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.00000500003, "input_dbu_cost_per_token": 0.000071429, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.000025000010000000002, "output_dbu_cost_per_token": 0.000357143, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "databricks/databricks/databricks-claude-sonnet-4", "slug": "databricks-databricks-databricks-claude-sonnet-4", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-claude-sonnet-4", "displayName": "databricks-claude-sonnet-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.9999900000000004, "outputUsdPer1MTokens": 15.000020000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.9999900000000004, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000029999900000000002, "input_dbu_cost_per_token": 0.000042857, "output_cost_per_token": 0.000015000020000000002, "output_dbu_cost_per_token": 0.000214286 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-claude-sonnet-4", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.0000029999900000000002, "input_dbu_cost_per_token": 0.000042857, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.000015000020000000002, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "databricks/databricks/databricks-claude-sonnet-4-1", "slug": "databricks-databricks-databricks-claude-sonnet-4-1", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-claude-sonnet-4-1", "displayName": "databricks-claude-sonnet-4-1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.9999900000000004, "outputUsdPer1MTokens": 15.000020000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.9999900000000004, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000029999900000000002, "input_dbu_cost_per_token": 0.000042857, "output_cost_per_token": 0.000015000020000000002, "output_dbu_cost_per_token": 0.000214286 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-claude-sonnet-4-1", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.0000029999900000000002, "input_dbu_cost_per_token": 0.000042857, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.000015000020000000002, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "databricks/databricks/databricks-claude-sonnet-4-5", "slug": "databricks-databricks-databricks-claude-sonnet-4-5", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-claude-sonnet-4-5", "displayName": "databricks-claude-sonnet-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.9999900000000004, "outputUsdPer1MTokens": 15.000020000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.9999900000000004, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000029999900000000002, "input_dbu_cost_per_token": 0.000042857, "output_cost_per_token": 0.000015000020000000002, "output_dbu_cost_per_token": 0.000214286 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-claude-sonnet-4-5", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.0000029999900000000002, "input_dbu_cost_per_token": 0.000042857, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.000015000020000000002, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "databricks/databricks/databricks-gemini-2-5-flash", "slug": "databricks-databricks-databricks-gemini-2-5-flash", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-gemini-2-5-flash", "displayName": "databricks-gemini-2-5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.30001999999999995, "outputUsdPer1MTokens": 2.49998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.30001999999999995, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.0001999999999996e-7, "input_dbu_cost_per_token": 0.000004285999999999999, "output_cost_per_token": 0.00000249998, "output_dbu_cost_per_token": 0.000035714 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-gemini-2-5-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 3.0001999999999996e-7, "input_dbu_cost_per_token": 0.000004285999999999999, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.00000249998, "output_dbu_cost_per_token": 0.000035714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "databricks/databricks/databricks-gemini-2-5-pro", "slug": "databricks-databricks-databricks-gemini-2-5-pro", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-gemini-2-5-pro", "displayName": "databricks-gemini-2-5-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.24999, "outputUsdPer1MTokens": 9.999990000000002, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.24999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000124999, "input_dbu_cost_per_token": 0.000017857, "output_cost_per_token": 0.000009999990000000002, "output_dbu_cost_per_token": 0.000142857 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-gemini-2-5-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.00000124999, "input_dbu_cost_per_token": 0.000017857, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.000009999990000000002, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "databricks/databricks/databricks-gemma-3-12b", "slug": "databricks-databricks-databricks-gemma-3-12b", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-gemma-3-12b", "displayName": "databricks-gemma-3-12b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15000999999999998, "outputUsdPer1MTokens": 0.5000100000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15000999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5000999999999998e-7, "input_dbu_cost_per_token": 0.0000021429999999999996, "output_cost_per_token": 5.0001e-7, "output_dbu_cost_per_token": 0.000007143 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 128000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-gemma-3-12b", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 1.5000999999999998e-7, "input_dbu_cost_per_token": 0.0000021429999999999996, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 32000, "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 5.0001e-7, "output_dbu_cost_per_token": 0.000007143, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "databricks/databricks/databricks-gpt-5", "slug": "databricks-databricks-databricks-gpt-5", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-gpt-5", "displayName": "databricks-gpt-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.24999, "outputUsdPer1MTokens": 9.999990000000002, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.24999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000124999, "input_dbu_cost_per_token": 0.000017857, "output_cost_per_token": 0.000009999990000000002, "output_dbu_cost_per_token": 0.000142857 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-gpt-5", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.00000124999, "input_dbu_cost_per_token": 0.000017857, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.000009999990000000002, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "databricks/databricks/databricks-gpt-5-1", "slug": "databricks-databricks-databricks-gpt-5-1", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-gpt-5-1", "displayName": "databricks-gpt-5-1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.24999, "outputUsdPer1MTokens": 9.999990000000002, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.24999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000124999, "input_dbu_cost_per_token": 0.000017857, "output_cost_per_token": 0.000009999990000000002, "output_dbu_cost_per_token": 0.000142857 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-gpt-5-1", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.00000124999, "input_dbu_cost_per_token": 0.000017857, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.000009999990000000002, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "databricks/databricks/databricks-gpt-5-mini", "slug": "databricks-databricks-databricks-gpt-5-mini", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-gpt-5-mini", "displayName": "databricks-gpt-5-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.24997000000000005, "outputUsdPer1MTokens": 1.9999700000000002, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.24997000000000005, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.4997000000000006e-7, "input_dbu_cost_per_token": 0.000003571, "output_cost_per_token": 0.0000019999700000000004, "output_dbu_cost_per_token": 0.000028571 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-gpt-5-mini", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 2.4997000000000006e-7, "input_dbu_cost_per_token": 0.000003571, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.0000019999700000000004, "output_dbu_cost_per_token": 0.000028571, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "databricks/databricks/databricks-gpt-5-nano", "slug": "databricks-databricks-databricks-gpt-5-nano", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-gpt-5-nano", "displayName": "databricks-gpt-5-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049980000000000004, "outputUsdPer1MTokens": 0.39998000000000006, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049980000000000004, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.998e-8, "input_dbu_cost_per_token": 7.14e-7, "output_cost_per_token": 3.9998000000000007e-7, "output_dbu_cost_per_token": 0.000005714000000000001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-gpt-5-nano", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 4.998e-8, "input_dbu_cost_per_token": 7.14e-7, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 3.9998000000000007e-7, "output_dbu_cost_per_token": 0.000005714000000000001, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "aime2025_accuracy_gpt5nanohigh_officiallaunchpost_28": { "label": "AIME 2025", "category": "reasoning", "score": 85.2, "scoreText": "85.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-nano", "exactModelOrSnapshot": "GPT-5 nano (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." } } }, { "id": "databricks/databricks/databricks-gpt-oss-120b", "slug": "databricks-databricks-databricks-gpt-oss-120b", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-gpt-oss-120b", "displayName": "databricks-gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15000999999999998, "outputUsdPer1MTokens": 0.59997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15000999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5000999999999998e-7, "input_dbu_cost_per_token": 0.0000021429999999999996, "output_cost_per_token": 5.9997e-7, "output_dbu_cost_per_token": 0.000008571 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-gpt-oss-120b", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 1.5000999999999998e-7, "input_dbu_cost_per_token": 0.0000021429999999999996, "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 5.9997e-7, "output_dbu_cost_per_token": 0.000008571, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "databricks/databricks/databricks-gpt-oss-20b", "slug": "databricks-databricks-databricks-gpt-oss-20b", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-gpt-oss-20b", "displayName": "databricks-gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.30001999999999995, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "input_dbu_cost_per_token": 0.000001, "output_cost_per_token": 3.0001999999999996e-7, "output_dbu_cost_per_token": 0.000004285999999999999 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-gpt-oss-20b", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 7e-8, "input_dbu_cost_per_token": 0.000001, "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 3.0001999999999996e-7, "output_dbu_cost_per_token": 0.000004285999999999999, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "databricks/databricks/databricks-gte-large-en", "slug": "databricks-databricks-databricks-gte-large-en", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-gte-large-en", "displayName": "databricks-gte-large-en", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.12999000000000002, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12999000000000002, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2999000000000001e-7, "input_dbu_cost_per_token": 0.000001857, "output_cost_per_token": 0, "output_dbu_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-gte-large-en", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 1.2999000000000001e-7, "input_dbu_cost_per_token": 0.000001857, "litellm_provider": "databricks", "max_input_tokens": 8192, "max_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "embedding", "output_cost_per_token": 0, "output_dbu_cost_per_token": 0, "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "benchmarks": { "local_mgteretrievaltable_avg_gtemultilingualbasedense_paper_344": { "label": "mGTE retrieval table", "category": "long_context", "score": 66.7, "scoreText": "66.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Dense", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_gtemultilingualbasesparse_paper_345": { "label": "mGTE retrieval table", "category": "long_context", "score": 57.2, "scoreText": "57.2", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Sparse", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_gtemultilingualbasedensesparse_paper_346": { "label": "mGTE retrieval table", "category": "long_context", "score": 68.9, "scoreText": "68.9", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Dense + Sparse", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "databricks/databricks/databricks-llama-2-70b-chat", "slug": "databricks-databricks-databricks-llama-2-70b-chat", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-llama-2-70b-chat", "displayName": "databricks-llama-2-70b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5000100000000001, "outputUsdPer1MTokens": 1.5000300000000002, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5000100000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.0001e-7, "input_dbu_cost_per_token": 0.000007143, "output_cost_per_token": 0.0000015000300000000002, "output_dbu_cost_per_token": 0.000021429 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-llama-2-70b-chat", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 5.0001e-7, "input_dbu_cost_per_token": 0.000007143, "litellm_provider": "databricks", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.0000015000300000000002, "output_dbu_cost_per_token": 0.000021429, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true } }, { "id": "databricks/databricks/databricks-llama-4-maverick", "slug": "databricks-databricks-databricks-llama-4-maverick", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-llama-4-maverick", "displayName": "databricks-llama-4-maverick", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5000100000000001, "outputUsdPer1MTokens": 1.5000300000000002, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5000100000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.0001e-7, "input_dbu_cost_per_token": 0.000007143, "output_cost_per_token": 0.0000015000300000000002, "output_dbu_cost_per_token": 0.000021429 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-llama-4-maverick", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 5.0001e-7, "input_dbu_cost_per_token": 0.000007143, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." }, "mode": "chat", "output_cost_per_token": 0.0000015000300000000002, "output_dbu_cost_per_token": 0.000021429, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "databricks/databricks/databricks-meta-llama-3-1-405b-instruct", "slug": "databricks-databricks-databricks-meta-llama-3-1-405b-instruct", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-meta-llama-3-1-405b-instruct", "displayName": "databricks-meta-llama-3-1-405b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.00003, "outputUsdPer1MTokens": 15.000020000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.00003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000500003, "input_dbu_cost_per_token": 0.000071429, "output_cost_per_token": 0.000015000020000000002, "output_dbu_cost_per_token": 0.000214286 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-meta-llama-3-1-405b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.00000500003, "input_dbu_cost_per_token": 0.000071429, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.000015000020000000002, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "databricks/databricks/databricks-meta-llama-3-1-8b-instruct", "slug": "databricks-databricks-databricks-meta-llama-3-1-8b-instruct", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-meta-llama-3-1-8b-instruct", "displayName": "databricks-meta-llama-3-1-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15000999999999998, "outputUsdPer1MTokens": 0.45003000000000004, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15000999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5000999999999998e-7, "input_dbu_cost_per_token": 0.0000021429999999999996, "output_cost_per_token": 4.5003000000000007e-7, "output_dbu_cost_per_token": 0.000006429000000000001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-meta-llama-3-1-8b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 1.5000999999999998e-7, "input_dbu_cost_per_token": 0.0000021429999999999996, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 4.5003000000000007e-7, "output_dbu_cost_per_token": 0.000006429000000000001, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "databricks/databricks/databricks-meta-llama-3-3-70b-instruct", "slug": "databricks-databricks-databricks-meta-llama-3-3-70b-instruct", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-meta-llama-3-3-70b-instruct", "displayName": "databricks-meta-llama-3-3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5000100000000001, "outputUsdPer1MTokens": 1.5000300000000002, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5000100000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.0001e-7, "input_dbu_cost_per_token": 0.000007143, "output_cost_per_token": 0.0000015000300000000002, "output_dbu_cost_per_token": 0.000021429 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-meta-llama-3-3-70b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 5.0001e-7, "input_dbu_cost_per_token": 0.000007143, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.0000015000300000000002, "output_dbu_cost_per_token": 0.000021429, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "databricks/databricks/databricks-meta-llama-3-70b-instruct", "slug": "databricks-databricks-databricks-meta-llama-3-70b-instruct", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-meta-llama-3-70b-instruct", "displayName": "databricks-meta-llama-3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.0000200000000001, "outputUsdPer1MTokens": 2.9999900000000004, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.0000200000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000100002, "input_dbu_cost_per_token": 0.000014286, "output_cost_per_token": 0.0000029999900000000002, "output_dbu_cost_per_token": 0.000042857 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-meta-llama-3-70b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.00000100002, "input_dbu_cost_per_token": 0.000014286, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.0000029999900000000002, "output_dbu_cost_per_token": 0.000042857, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true } }, { "id": "databricks/databricks/databricks-mixtral-8x7b-instruct", "slug": "databricks-databricks-databricks-mixtral-8x7b-instruct", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-mixtral-8x7b-instruct", "displayName": "databricks-mixtral-8x7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5000100000000001, "outputUsdPer1MTokens": 1.0000200000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5000100000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.0001e-7, "input_dbu_cost_per_token": 0.000007143, "output_cost_per_token": 0.00000100002, "output_dbu_cost_per_token": 0.000014286 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-mixtral-8x7b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 5.0001e-7, "input_dbu_cost_per_token": 0.000007143, "litellm_provider": "databricks", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.00000100002, "output_dbu_cost_per_token": 0.000014286, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true } }, { "id": "databricks/databricks/databricks-mpt-30b-instruct", "slug": "databricks-databricks-databricks-mpt-30b-instruct", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-mpt-30b-instruct", "displayName": "databricks-mpt-30b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.0000200000000001, "outputUsdPer1MTokens": 1.0000200000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.0000200000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000100002, "input_dbu_cost_per_token": 0.000014286, "output_cost_per_token": 0.00000100002, "output_dbu_cost_per_token": 0.000014286 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-mpt-30b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 0.00000100002, "input_dbu_cost_per_token": 0.000014286, "litellm_provider": "databricks", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0.00000100002, "output_dbu_cost_per_token": 0.000014286, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true } }, { "id": "databricks/databricks/databricks-mpt-7b-instruct", "slug": "databricks-databricks-databricks-mpt-7b-instruct", "provider": "databricks", "providerSlug": "databricks", "name": "databricks-mpt-7b-instruct", "displayName": "databricks-mpt-7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5000100000000001, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5000100000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.0001e-7, "input_dbu_cost_per_token": 0.000007143, "output_cost_per_token": 0, "output_dbu_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "databricks/databricks-mpt-7b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "rawLitellm": { "input_cost_per_token": 5.0001e-7, "input_dbu_cost_per_token": 0.000007143, "litellm_provider": "databricks", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 0, "output_dbu_cost_per_token": 0, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true } }, { "id": "dataforseo/dataforseo/search", "slug": "dataforseo-dataforseo-search", "provider": "dataforseo", "providerSlug": "dataforseo", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 3, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dataforseo/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.003, "litellm_provider": "dataforseo", "mode": "search", "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "text-completion-openai/davinci-002", "slug": "text-completion-openai-davinci-002", "provider": "text-completion-openai", "providerSlug": "text-completion-openai", "name": "davinci-002", "displayName": "davinci-002", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "davinci-002", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.000002 } }, { "id": "deepgram/deepgram/base", "slug": "deepgram-deepgram-base", "provider": "deepgram", "providerSlug": "deepgram", "name": "base", "displayName": "base", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00020833, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00020833, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/base", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/base-conversationalai", "slug": "deepgram-deepgram-base-conversationalai", "provider": "deepgram", "providerSlug": "deepgram", "name": "base-conversationalai", "displayName": "base-conversationalai", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00020833, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00020833, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/base-conversationalai", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/base-finance", "slug": "deepgram-deepgram-base-finance", "provider": "deepgram", "providerSlug": "deepgram", "name": "base-finance", "displayName": "base-finance", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00020833, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00020833, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/base-finance", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/base-general", "slug": "deepgram-deepgram-base-general", "provider": "deepgram", "providerSlug": "deepgram", "name": "base-general", "displayName": "base-general", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00020833, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00020833, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/base-general", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/base-meeting", "slug": "deepgram-deepgram-base-meeting", "provider": "deepgram", "providerSlug": "deepgram", "name": "base-meeting", "displayName": "base-meeting", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00020833, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00020833, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/base-meeting", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/base-phonecall", "slug": "deepgram-deepgram-base-phonecall", "provider": "deepgram", "providerSlug": "deepgram", "name": "base-phonecall", "displayName": "base-phonecall", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00020833, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00020833, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/base-phonecall", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/base-video", "slug": "deepgram-deepgram-base-video", "provider": "deepgram", "providerSlug": "deepgram", "name": "base-video", "displayName": "base-video", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00020833, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00020833, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/base-video", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/base-voicemail", "slug": "deepgram-deepgram-base-voicemail", "provider": "deepgram", "providerSlug": "deepgram", "name": "base-voicemail", "displayName": "base-voicemail", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00020833, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00020833, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/base-voicemail", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/enhanced", "slug": "deepgram-deepgram-enhanced", "provider": "deepgram", "providerSlug": "deepgram", "name": "enhanced", "displayName": "enhanced", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00024167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00024167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/enhanced", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/enhanced-finance", "slug": "deepgram-deepgram-enhanced-finance", "provider": "deepgram", "providerSlug": "deepgram", "name": "enhanced-finance", "displayName": "enhanced-finance", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00024167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00024167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/enhanced-finance", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/enhanced-general", "slug": "deepgram-deepgram-enhanced-general", "provider": "deepgram", "providerSlug": "deepgram", "name": "enhanced-general", "displayName": "enhanced-general", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00024167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00024167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/enhanced-general", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/enhanced-meeting", "slug": "deepgram-deepgram-enhanced-meeting", "provider": "deepgram", "providerSlug": "deepgram", "name": "enhanced-meeting", "displayName": "enhanced-meeting", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00024167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00024167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/enhanced-meeting", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/enhanced-phonecall", "slug": "deepgram-deepgram-enhanced-phonecall", "provider": "deepgram", "providerSlug": "deepgram", "name": "enhanced-phonecall", "displayName": "enhanced-phonecall", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00024167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00024167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/enhanced-phonecall", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova", "slug": "deepgram-deepgram-nova", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova", "displayName": "nova", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2", "slug": "deepgram-deepgram-nova-2", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2", "displayName": "nova-2", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2-atc", "slug": "deepgram-deepgram-nova-2-atc", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2-atc", "displayName": "nova-2-atc", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2-atc", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2-automotive", "slug": "deepgram-deepgram-nova-2-automotive", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2-automotive", "displayName": "nova-2-automotive", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2-automotive", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2-conversationalai", "slug": "deepgram-deepgram-nova-2-conversationalai", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2-conversationalai", "displayName": "nova-2-conversationalai", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2-conversationalai", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2-drivethru", "slug": "deepgram-deepgram-nova-2-drivethru", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2-drivethru", "displayName": "nova-2-drivethru", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2-drivethru", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2-finance", "slug": "deepgram-deepgram-nova-2-finance", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2-finance", "displayName": "nova-2-finance", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2-finance", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2-general", "slug": "deepgram-deepgram-nova-2-general", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2-general", "displayName": "nova-2-general", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2-general", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2-meeting", "slug": "deepgram-deepgram-nova-2-meeting", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2-meeting", "displayName": "nova-2-meeting", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2-meeting", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2-phonecall", "slug": "deepgram-deepgram-nova-2-phonecall", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2-phonecall", "displayName": "nova-2-phonecall", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2-phonecall", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2-video", "slug": "deepgram-deepgram-nova-2-video", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2-video", "displayName": "nova-2-video", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2-video", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-2-voicemail", "slug": "deepgram-deepgram-nova-2-voicemail", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-2-voicemail", "displayName": "nova-2-voicemail", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-2-voicemail", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-3", "slug": "deepgram-deepgram-nova-3", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-3", "displayName": "nova-3", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-3", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-3-general", "slug": "deepgram-deepgram-nova-3-general", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-3-general", "displayName": "nova-3-general", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-3-general", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-3-medical", "slug": "deepgram-deepgram-nova-3-medical", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-3-medical", "displayName": "nova-3-medical", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00008667, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00008667, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-3-medical", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00008667, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0052/60 seconds = $0.00008667 per second (multilingual)", "original_pricing_per_minute": 0.0052 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-general", "slug": "deepgram-deepgram-nova-general", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-general", "displayName": "nova-general", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-general", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/nova-phonecall", "slug": "deepgram-deepgram-nova-phonecall", "provider": "deepgram", "providerSlug": "deepgram", "name": "nova-phonecall", "displayName": "nova-phonecall", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00007167, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00007167, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/nova-phonecall", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.00007167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/whisper", "slug": "deepgram-deepgram-whisper", "provider": "deepgram", "providerSlug": "deepgram", "name": "whisper", "displayName": "whisper", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0001, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/whisper", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/whisper-base", "slug": "deepgram-deepgram-whisper-base", "provider": "deepgram", "providerSlug": "deepgram", "name": "whisper-base", "displayName": "whisper-base", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0001, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/whisper-base", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/whisper-large", "slug": "deepgram-deepgram-whisper-large", "provider": "deepgram", "providerSlug": "deepgram", "name": "whisper-large", "displayName": "whisper-large", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0001, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/whisper-large", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/whisper-medium", "slug": "deepgram-deepgram-whisper-medium", "provider": "deepgram", "providerSlug": "deepgram", "name": "whisper-medium", "displayName": "whisper-medium", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0001, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/whisper-medium", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/whisper-small", "slug": "deepgram-deepgram-whisper-small", "provider": "deepgram", "providerSlug": "deepgram", "name": "whisper-small", "displayName": "whisper-small", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0001, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/whisper-small", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepgram/deepgram/whisper-tiny", "slug": "deepgram-deepgram-whisper-tiny", "provider": "deepgram", "providerSlug": "deepgram", "name": "whisper-tiny", "displayName": "whisper-tiny", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0001, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepgram/whisper-tiny", "syncedAt": "2026-05-28", "sourceUrl": "https://deepgram.com/pricing" }, "rawLitellm": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "deepinfra/deepinfra/Gryphe/MythoMax-L2-13b", "slug": "deepinfra-deepinfra-gryphe-mythomax-l2-13b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "MythoMax-L2-13b", "displayName": "MythoMax-L2-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.09, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 9e-8 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Gryphe/MythoMax-L2-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 8e-8, "output_cost_per_token": 9e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Gryphe/MythoMax-L2-13b" ], "manual_model_modalities_note": "HF model card labels this model as text generation." } }, { "id": "deepinfra/deepinfra/NousResearch/Hermes-3-Llama-3.1-405B", "slug": "deepinfra-deepinfra-nousresearch-hermes-3-llama-3-1-405b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Hermes-3-Llama-3.1-405B", "displayName": "Hermes-3-Llama-3.1-405B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B" ], "manual_model_modalities_note": "HF model card labels this model as text generation." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "deepinfra/deepinfra/NousResearch/Hermes-3-Llama-3.1-70B", "slug": "deepinfra-deepinfra-nousresearch-hermes-3-llama-3-1-70b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Hermes-3-Llama-3.1-70B", "displayName": "Hermes-3-Llama-3.1-70B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B" ], "manual_model_modalities_note": "HF model card labels this model as text generation." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "deepinfra/deepinfra/Qwen/QwQ-32B", "slug": "deepinfra-deepinfra-qwen-qwq-32b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "QwQ-32B", "displayName": "QwQ-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/QwQ-32B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/QwQ-32B" ], "manual_model_modalities_note": "HF model card labels this model as text generation." } }, { "id": "deepinfra/deepinfra/Qwen/Qwen2.5-72B-Instruct", "slug": "deepinfra-deepinfra-qwen-qwen2-5-72b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen2.5-72B-Instruct", "displayName": "Qwen2.5-72B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.39, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3.9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen2.5-72B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3.9e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct" ], "manual_model_modalities_note": "HF model card labels this model as text generation." }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." } } }, { "id": "deepinfra/deepinfra/Qwen/Qwen2.5-7B-Instruct", "slug": "deepinfra-deepinfra-qwen-qwen2-5-7b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen2.5-7B-Instruct", "displayName": "Qwen2.5-7B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen2.5-7B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-8, "output_cost_per_token": 1e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen2.5-7B-Instruct" ], "manual_model_modalities_note": "HF model card labels this model as text generation." }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." } } }, { "id": "deepinfra/deepinfra/Qwen/Qwen2.5-VL-32B-Instruct", "slug": "deepinfra-deepinfra-qwen-qwen2-5-vl-32b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen2.5-VL-32B-Instruct", "displayName": "Qwen2.5-VL-32B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": true, "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_vision": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.deepinfra.com/chat/vision", "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct" ], "manual_model_modalities_note": "DeepInfra vision docs and HF model card show image-text-to-text usage." }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_mmmu_score_qwen25vl32b_officialmodelcard_374": { "label": "MMMU", "category": "multimodal", "score": 70, "scoreText": "70", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mmmupro_score_qwen25vl32b_officialmodelcard_375": { "label": "MMMU-Pro", "category": "multimodal", "score": 49.5, "scoreText": "49.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mmstar_score_qwen25vl32b_officialmodelcard_376": { "label": "MMStar", "category": "multimodal", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mathvista_score_qwen25vl32b_officialmodelcard_377": { "label": "MathVista", "category": "multimodal", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mathvision_score_qwen25vl32b_officialmodelcard_378": { "label": "MathVision", "category": "multimodal", "score": 40, "scoreText": "40.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_ccocr_score_qwen25vl32b_officialmodelcard_379": { "label": "CC-OCR", "category": "multimodal", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_docvqa_score_qwen25vl32b_officialmodelcard_380": { "label": "DocVQA", "category": "multimodal", "score": 94.8, "scoreText": "94.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_infovqa_score_qwen25vl32b_officialmodelcard_381": { "label": "InfoVQA", "category": "multimodal", "score": 83.4, "scoreText": "83.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." } } }, { "id": "deepinfra/deepinfra/Qwen/Qwen3-14B", "slug": "deepinfra-deepinfra-qwen-qwen3-14b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen3-14B", "displayName": "Qwen3-14B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen3-14B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/Qwen/Qwen3-14B", "https://huggingface.co/Qwen/Qwen3-14B" ], "manual_model_modalities_note": "DeepInfra model page and HF model card label this model as text generation." } }, { "id": "deepinfra/deepinfra/Qwen/Qwen3-235B-A22B", "slug": "deepinfra-deepinfra-qwen-qwen3-235b-a22b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen3-235B-A22B", "displayName": "Qwen3-235B-A22B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": 0.54, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 5.4e-7 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen3-235B-A22B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 5.4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/qwen", "https://huggingface.co/Qwen/Qwen3-235B-A22B" ], "manual_model_modalities_note": "DeepInfra Qwen page and HF model card label this model as text generation." } }, { "id": "deepinfra/deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507", "slug": "deepinfra-deepinfra-qwen-qwen3-235b-a22b-instruct-2507", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen3-235B-A22B-Instruct-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-8, "output_cost_per_token": 6e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://status.deepinfra.com/", "https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507" ], "manual_model_modalities_note": "HF model card labels this model as a causal language model." } }, { "id": "deepinfra/deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507", "slug": "deepinfra-deepinfra-qwen-qwen3-235b-a22b-thinking-2507", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen3-235B-A22B-Thinking-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.9000000000000004, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000029 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000029, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/Qwen/Qwen3-235B-A22B-Thinking-2507", "https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507" ], "manual_model_modalities_note": "DeepInfra model page and HF model card label this model as text generation." } }, { "id": "deepinfra/deepinfra/Qwen/Qwen3-30B-A3B", "slug": "deepinfra-deepinfra-qwen-qwen3-30b-a3b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen3-30B-A3B", "displayName": "Qwen3-30B-A3B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.29, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 2.9e-7 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen3-30B-A3B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 8e-8, "output_cost_per_token": 2.9e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.deepinfra.com/integrations/anthropic", "https://huggingface.co/Qwen/Qwen3-30B-A3B" ], "manual_model_modalities_note": "HF model card labels this model as text generation." } }, { "id": "deepinfra/deepinfra/Qwen/Qwen3-32B", "slug": "deepinfra-deepinfra-qwen-qwen3-32b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen3-32B", "displayName": "Qwen3-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen3-32B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-7, "output_cost_per_token": 2.8e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen3-32B" ], "manual_model_modalities_note": "HF model card labels this model as text generation." } }, { "id": "deepinfra/deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct", "slug": "deepinfra-deepinfra-qwen-qwen3-coder-480b-a35b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen3-Coder-480B-A35B-Instruct", "displayName": "Qwen3-Coder-480B-A35B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "https://qwenlm.github.io/blog/qwen3-coder/" ], "manual_model_modalities_note": "HF model card labels this model as text generation." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "deepinfra/deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "slug": "deepinfra-deepinfra-qwen-qwen3-coder-480b-a35b-instruct-turbo", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen3-Coder-480B-A35B-Instruct-Turbo", "displayName": "Qwen3-Coder-480B-A35B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.29, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.29, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.9e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.9e-7, "output_cost_per_token": 0.0000012, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct" ], "manual_model_modalities_note": "DeepInfra model page and HF model card label this model as text generation." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "deepinfra/deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct", "slug": "deepinfra-deepinfra-qwen-qwen3-next-80b-a3b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen3-Next-80B-A3B-Instruct", "displayName": "Qwen3-Next-80B-A3B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.14, "outputUsdPer1MTokens": 1.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.14, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 0.0000014 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 0.0000014, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct" ], "manual_model_modalities_note": "HF model card labels this model as text generation." }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "deepinfra/deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking", "slug": "deepinfra-deepinfra-qwen-qwen3-next-80b-a3b-thinking", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Qwen3-Next-80B-A3B-Thinking", "displayName": "Qwen3-Next-80B-A3B-Thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.14, "outputUsdPer1MTokens": 1.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.14, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 0.0000014 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 0.0000014, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking" ], "manual_model_modalities_note": "HF model card labels this model as text generation." }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "deepinfra/deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo", "slug": "deepinfra-deepinfra-sao10k-l3-8b-lunaris-v1-turbo", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "L3-8B-Lunaris-v1-Turbo", "displayName": "L3-8B-Lunaris-v1-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.049999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 5e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 4e-8, "output_cost_per_token": 5e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/models/text-generation/2" ], "manual_model_modalities_note": "DeepInfra lists the exact alias under the text generation catalog." } }, { "id": "deepinfra/deepinfra/Sao10K/L3.1-70B-Euryale-v2.2", "slug": "deepinfra-deepinfra-sao10k-l3-1-70b-euryale-v2-2", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "L3.1-70B-Euryale-v2.2", "displayName": "L3.1-70B-Euryale-v2.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.65, "outputUsdPer1MTokens": 0.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 7.5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.5e-7, "output_cost_per_token": 7.5e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Sao10K/L3.1-70B-Euryale-v2.2", "https://huggingface.co/Sao10K/models" ], "manual_model_modalities_note": "HF model page shows text generation." } }, { "id": "deepinfra/deepinfra/Sao10K/L3.3-70B-Euryale-v2.3", "slug": "deepinfra-deepinfra-sao10k-l3-3-70b-euryale-v2-3", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "L3.3-70B-Euryale-v2.3", "displayName": "L3.3-70B-Euryale-v2.3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.65, "outputUsdPer1MTokens": 0.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 7.5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.5e-7, "output_cost_per_token": 7.5e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3" ], "manual_model_modalities_note": "HF model page shows text generation." } }, { "id": "deepinfra/deepinfra/allenai/olmOCR-7B-0725-FP8", "slug": "deepinfra-deepinfra-allenai-olmocr-7b-0725-fp8", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "olmOCR-7B-0725-FP8", "displayName": "olmOCR-7B-0725-FP8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/allenai/olmOCR-7B-0725-FP8", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.0000015, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/allenai/olmOCR-7B-0725-FP8" ], "manual_model_modalities_note": "HF model page labels the task image-text-to-text." } }, { "id": "deepinfra/deepinfra/anthropic/claude-3-7-sonnet-latest", "slug": "deepinfra-deepinfra-anthropic-claude-3-7-sonnet-latest", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "claude-3-7-sonnet-latest", "displayName": "claude-3-7-sonnet-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "cache_read_input_token_cost": 3.3e-7 } }, "limits": { "contextWindow": 200000, "maxInputTokens": 200000, "maxOutputTokens": 200000, "maxTokens": 200000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/anthropic/claude-3-7-sonnet-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "cache_read_input_token_cost": 3.3e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://www.anthropic.com/news/claude-3-7-sonnet" ], "manual_model_modalities_note": "Anthropic docs describe Claude 3.7 Sonnet as supporting text and image input with text output." }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "deepinfra/deepinfra/anthropic/claude-4-opus", "slug": "deepinfra-deepinfra-anthropic-claude-4-opus", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "claude-4-opus", "displayName": "claude-4-opus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 16.5, "outputUsdPer1MTokens": 82.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 16.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.0000825 } }, "limits": { "contextWindow": 200000, "maxInputTokens": 200000, "maxOutputTokens": 200000, "maxTokens": 200000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/anthropic/claude-4-opus", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.0000825, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Anthropic docs describe current Claude models as supporting text and image input with text output." } }, { "id": "deepinfra/deepinfra/anthropic/claude-4-sonnet", "slug": "deepinfra-deepinfra-anthropic-claude-4-sonnet", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "claude-4-sonnet", "displayName": "claude-4-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 200000, "maxInputTokens": 200000, "maxOutputTokens": 200000, "maxTokens": 200000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/anthropic/claude-4-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Anthropic docs describe current Claude models as supporting text and image input with text output." } }, { "id": "deepinfra/deepinfra/deepseek-ai/DeepSeek-R1", "slug": "deepinfra-deepinfra-deepseek-ai-deepseek-r1", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "DeepSeek-R1", "displayName": "DeepSeek-R1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/deepseek-ai/DeepSeek-R1", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000024, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.deepinfra.com/chat/reasoning", "https://huggingface.co/deepseek-ai/DeepSeek-R1" ], "manual_model_modalities_note": "DeepInfra reasoning docs and HF model card label this model as text generation." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "deepinfra/deepinfra/deepseek-ai/DeepSeek-R1-0528", "slug": "deepinfra-deepinfra-deepseek-ai-deepseek-r1-0528", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "DeepSeek-R1-0528", "displayName": "DeepSeek-R1-0528", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 2.1500000000000004, "cachedInputUsdPer1MTokens": 0.39999999999999997, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.00000215, "cache_read_input_token_cost": 4e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/deepseek-ai/DeepSeek-R1-0528", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.00000215, "cache_read_input_token_cost": 4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/deepseek-ai/DeepSeek-R1-0528" ], "manual_model_modalities_note": "DeepInfra model page labels this model as text generation." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "deepinfra/deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo", "slug": "deepinfra-deepinfra-deepseek-ai-deepseek-r1-0528-turbo", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "DeepSeek-R1-0528-Turbo", "displayName": "DeepSeek-R1-0528-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/deepseek-ai/DeepSeek-R1-0528-Turbo" ], "manual_model_modalities_note": "DeepInfra exact model page serializes this alias as type text-generation." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "deepinfra/deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "slug": "deepinfra-deepinfra-deepseek-ai-deepseek-r1-distill-llama-70b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "DeepSeek-R1-Distill-Llama-70B", "displayName": "DeepSeek-R1-Distill-Llama-70B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/deepseek-ai/DeepSeek-R1-Distill-Llama-70B" ], "manual_model_modalities_note": "DeepInfra model page labels this model as text generation." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "deepinfra/deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "slug": "deepinfra-deepinfra-deepseek-ai-deepseek-r1-distill-qwen-32b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "DeepSeek-R1-Distill-Qwen-32B", "displayName": "DeepSeek-R1-Distill-Qwen-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 0.27, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 2.7e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 2.7e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B" ], "manual_model_modalities_note": "Official model page labels this model as text generation." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "deepinfra/deepinfra/deepseek-ai/DeepSeek-R1-Turbo", "slug": "deepinfra-deepinfra-deepseek-ai-deepseek-r1-turbo", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "DeepSeek-R1-Turbo", "displayName": "DeepSeek-R1-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/deepseek-ai/DeepSeek-R1-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/deepseek-ai/DeepSeek-R1-Turbo" ], "manual_model_modalities_note": "DeepInfra exact model page serializes this alias as type text-generation." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "deepinfra/deepinfra/deepseek-ai/DeepSeek-V3", "slug": "deepinfra-deepinfra-deepseek-ai-deepseek-v3", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "DeepSeek-V3", "displayName": "DeepSeek-V3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.38, "outputUsdPer1MTokens": 0.8899999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.8e-7, "output_cost_per_token": 8.9e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/deepseek-ai/DeepSeek-V3", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 3.8e-7, "output_cost_per_token": 8.9e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/deepseek-ai/DeepSeek-V3" ], "manual_model_modalities_note": "DeepInfra model page labels this model as text generation." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "deepinfra/deepinfra/deepseek-ai/DeepSeek-V3-0324", "slug": "deepinfra-deepinfra-deepseek-ai-deepseek-v3-0324", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "DeepSeek-V3-0324", "displayName": "DeepSeek-V3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/deepseek-ai/DeepSeek-V3-0324", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 8.8e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://api-docs.deepseek.com/news/news250325", "https://api-docs.deepseek.com/updates" ], "manual_model_modalities_note": "Official DeepSeek release notes indicate text-only chat usage." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "deepinfra/deepinfra/deepseek-ai/DeepSeek-V3.1", "slug": "deepinfra-deepinfra-deepseek-ai-deepseek-v3-1", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "DeepSeek-V3.1", "displayName": "DeepSeek-V3.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": 0.216, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "cache_read_input_token_cost": 2.16e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "reasoning": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/deepseek-ai/DeepSeek-V3.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "cache_read_input_token_cost": 2.16e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_reasoning": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://api-docs.deepseek.com/news/news250821", "https://api-docs.deepseek.com/updates" ], "manual_model_modalities_note": "Official DeepSeek release notes indicate text-only chat usage." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "deepinfra/deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus", "slug": "deepinfra-deepinfra-deepseek-ai-deepseek-v3-1-terminus", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "DeepSeek-V3.1-Terminus", "displayName": "DeepSeek-V3.1-Terminus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": 0.216, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "cache_read_input_token_cost": 2.16e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "cache_read_input_token_cost": 2.16e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.deepinfra.com/integrations/anthropic", "https://api-docs.deepseek.com/news/news250922", "https://api-docs.deepseek.com/updates" ], "manual_model_modalities_note": "DeepInfra docs and DeepSeek release notes indicate text-only chat usage." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "deepinfra/deepinfra/google/gemini-2.0-flash-001", "slug": "deepinfra-deepinfra-google-gemini-2-0-flash-001", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "gemini-2.0-flash-001", "displayName": "gemini-2.0-flash-001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 1000000, "maxInputTokens": 1000000, "maxOutputTokens": 1000000, "maxTokens": 1000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "audio", "code", "image", "text", "video" ], "input": [ "audio", "code", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01" }, "source": { "type": "litellm", "litellmKey": "deepinfra/google/gemini-2.0-flash-001", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-06-01", "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/2-0-flash" ], "manual_model_modalities_note": "Official Google model page lists supported inputs and text output." }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." } } }, { "id": "deepinfra/deepinfra/google/gemini-2.5-flash", "slug": "deepinfra-deepinfra-google-gemini-2-5-flash", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "gemini-2.5-flash", "displayName": "gemini-2.5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 1000000, "maxInputTokens": 1000000, "maxOutputTokens": 1000000, "maxTokens": 1000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "audio", "code", "image", "text", "video" ], "input": [ "audio", "code", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/google/gemini-2.5-flash", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/2-5-flash" ], "manual_model_modalities_note": "Official Google model page lists supported inputs and text output." } }, { "id": "deepinfra/deepinfra/google/gemini-2.5-pro", "slug": "deepinfra-deepinfra-google-gemini-2-5-pro", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "gemini-2.5-pro", "displayName": "gemini-2.5-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 1000000, "maxInputTokens": 1000000, "maxOutputTokens": 1000000, "maxTokens": 1000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "audio", "code", "image", "text", "video" ], "input": [ "audio", "code", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/google/gemini-2.5-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/2-5-pro" ], "manual_model_modalities_note": "Official Google model page lists supported inputs and text output." }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "deepinfra/deepinfra/google/gemma-3-12b-it", "slug": "deepinfra-deepinfra-google-gemma-3-12b-it", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "gemma-3-12b-it", "displayName": "gemma-3-12b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/google/gemma-3-12b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/google/gemma-3-12b-it" ], "manual_model_modalities_note": "Official model page labels this model as image-text-to-text." }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "deepinfra/deepinfra/google/gemma-3-27b-it", "slug": "deepinfra-deepinfra-google-gemma-3-27b-it", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "gemma-3-27b-it", "displayName": "gemma-3-27b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.16, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 1.6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/google/gemma-3-27b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-8, "output_cost_per_token": 1.6e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/google/gemma-3-27b-it" ], "manual_model_modalities_note": "Official model page labels this model as image-text-to-text." }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "deepinfra/deepinfra/google/gemma-3-4b-it", "slug": "deepinfra-deepinfra-google-gemma-3-4b-it", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "gemma-3-4b-it", "displayName": "gemma-3-4b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/google/gemma-3-4b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-8, "output_cost_per_token": 8e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/google/gemma-3-4b-it" ], "manual_model_modalities_note": "Google model card says Gemma 3 supports text and image input with text output." }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "deepinfra/deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct", "slug": "deepinfra-deepinfra-meta-llama-llama-3-2-11b-vision-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Llama-3.2-11B-Vision-Instruct", "displayName": "Llama-3.2-11B-Vision-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049, "outputUsdPer1MTokens": 0.049, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.9e-8, "output_cost_per_token": 4.9e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4.9e-8, "output_cost_per_token": 4.9e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.deepinfra.com/chat/vision" ], "manual_model_modalities_note": "DeepInfra vision docs list this exact alias as an image-plus-text to text model." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "deepinfra/deepinfra/meta-llama/Llama-3.2-3B-Instruct", "slug": "deepinfra-deepinfra-meta-llama-llama-3-2-3b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Llama-3.2-3B-Instruct", "displayName": "Llama-3.2-3B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": 0.02, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 2e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Llama-3.2-3B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-8, "output_cost_per_token": 2e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" ], "manual_model_modalities_note": "Meta model card labels this model as text only." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "deepinfra/deepinfra/meta-llama/Llama-3.3-70B-Instruct", "slug": "deepinfra-deepinfra-meta-llama-llama-3-3-70b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.3e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Llama-3.3-70B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.3e-7, "output_cost_per_token": 4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct" ], "manual_model_modalities_note": "Meta model card labels this model as text only." }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "deepinfra/deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo", "slug": "deepinfra-deepinfra-meta-llama-llama-3-3-70b-instruct-turbo", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Llama-3.3-70B-Instruct-Turbo", "displayName": "Llama-3.3-70B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.39, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 3.9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 3.9e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/meta-llama/Llama-3.3-70B-Instruct-Turbo" ], "manual_model_modalities_note": "DeepInfra model page says text-only input and generated text/code output." }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "deepinfra/deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "slug": "deepinfra-deepinfra-meta-llama-llama-4-maverick-17b-128e-instruct-fp8", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Llama-4-Maverick-17B-128E-Instruct-FP8", "displayName": "Llama-4-Maverick-17B-128E-Instruct-FP8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 1048576, "maxInputTokens": 1048576, "maxOutputTokens": 1048576, "maxTokens": 1048576, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8" ], "manual_model_modalities_note": "Meta model card says Maverick takes text and image input with text output." }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "deepinfra/deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct", "slug": "deepinfra-deepinfra-meta-llama-llama-4-scout-17b-16e-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Llama-4-Scout-17B-16E-Instruct", "displayName": "Llama-4-Scout-17B-16E-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 327680, "maxInputTokens": 327680, "maxOutputTokens": 327680, "maxTokens": 327680, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 327680, "max_input_tokens": 327680, "max_output_tokens": 327680, "input_cost_per_token": 8e-8, "output_cost_per_token": 3e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct" ], "manual_model_modalities_note": "Meta model card says Scout takes text and image input with text output." }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "deepinfra/deepinfra/meta-llama/Llama-Guard-3-8B", "slug": "deepinfra-deepinfra-meta-llama-llama-guard-3-8b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Llama-Guard-3-8B", "displayName": "Llama-Guard-3-8B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.055, "outputUsdPer1MTokens": 0.055, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.055, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-8, "output_cost_per_token": 5.5e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Llama-Guard-3-8B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5.5e-8, "output_cost_per_token": 5.5e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/meta-llama/Llama-Guard-3-8B" ], "manual_model_modalities_note": "DeepInfra model page describes a text-generation safety classifier." } }, { "id": "deepinfra/deepinfra/meta-llama/Llama-Guard-4-12B", "slug": "deepinfra-deepinfra-meta-llama-llama-guard-4-12b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Llama-Guard-4-12B", "displayName": "Llama-Guard-4-12B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": 0.18, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 1.8e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Llama-Guard-4-12B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 1.8e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/meta-llama/Llama-Guard-4-12B" ], "manual_model_modalities_note": "DeepInfra model page says the model is trained on text and multiple images and generates text output." } }, { "id": "deepinfra/deepinfra/meta-llama/Meta-Llama-3-8B-Instruct", "slug": "deepinfra-deepinfra-meta-llama-meta-llama-3-8b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Meta-Llama-3-8B-Instruct", "displayName": "Meta-Llama-3-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.03, "outputUsdPer1MTokens": 0.06, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.03, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-8, "output_cost_per_token": 6e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 3e-8, "output_cost_per_token": 6e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/meta-llama/Meta-Llama-3-8B-Instruct" ], "manual_model_modalities_note": "DeepInfra model page says input is text-only and output is text/code." } }, { "id": "deepinfra/deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct", "slug": "deepinfra-deepinfra-meta-llama-meta-llama-3-1-70b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Meta-Llama-3.1-70B-Instruct", "displayName": "Meta-Llama-3.1-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-7, "output_cost_per_token": 4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/meta-llama/Meta-Llama-3.1-70B-Instruct" ], "manual_model_modalities_note": "DeepInfra model page says the model is text in/text out, with text/code outputs." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "deepinfra/deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "slug": "deepinfra-deepinfra-meta-llama-meta-llama-3-1-70b-instruct-turbo", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Meta-Llama-3.1-70B-Instruct-Turbo", "displayName": "Meta-Llama-3.1-70B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 2.8e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" ], "manual_model_modalities_note": "DeepInfra model page says the model is text in/text out, with text/code outputs." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "deepinfra/deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct", "slug": "deepinfra-deepinfra-meta-llama-meta-llama-3-1-8b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Meta-Llama-3.1-8B-Instruct", "displayName": "Meta-Llama-3.1-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.03, "outputUsdPer1MTokens": 0.049999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.03, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-8, "output_cost_per_token": 5e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-8, "output_cost_per_token": 5e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.deepinfra.com/private-models/lora", "https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct" ], "manual_model_modalities_note": "DeepInfra LoRA docs and Meta model card label this model as text generation." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "deepinfra/deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "slug": "deepinfra-deepinfra-meta-llama-meta-llama-3-1-8b-instruct-turbo", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Meta-Llama-3.1-8B-Instruct-Turbo", "displayName": "Meta-Llama-3.1-8B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": 0.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 3e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-8, "output_cost_per_token": 3e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo" ], "manual_model_modalities_note": "Official page labels it as text-only with generated text output." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "deepinfra/deepinfra/microsoft/WizardLM-2-8x22B", "slug": "deepinfra-deepinfra-microsoft-wizardlm-2-8x22b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "WizardLM-2-8x22B", "displayName": "WizardLM-2-8x22B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.48, "outputUsdPer1MTokens": 0.48, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.48, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.8e-7, "output_cost_per_token": 4.8e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/microsoft/WizardLM-2-8x22B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 4.8e-7, "output_cost_per_token": 4.8e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/microsoft/WizardLM-2-8x22B" ], "manual_model_modalities_note": "DeepInfra exact model page serializes this alias as type text-generation." } }, { "id": "deepinfra/deepinfra/microsoft/phi-4", "slug": "deepinfra-deepinfra-microsoft-phi-4", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "phi-4", "displayName": "phi-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.14, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 1.4e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/microsoft/phi-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 7e-8, "output_cost_per_token": 1.4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/microsoft/phi-4" ], "manual_model_modalities_note": "Official model page says inputs are text and outputs are generated text." }, "benchmarks": { "mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_202": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "gpqa_science_phi414b_officialmodelcard_203": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "humaneval_codegeneration_phi414b_officialmodelcard_204": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "drop_reasoning_phi414b_officialmodelcard_205": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "local_mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_160": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_gpqa_science_phi414b_officialmodelcard_161": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_humaneval_codegeneration_phi414b_officialmodelcard_162": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_simpleqa_factualknowledge_phi414b_officialmodelcard_163": { "label": "SimpleQA", "category": "general_knowledge", "score": 3, "scoreText": "3.0", "metric": "Factual Knowledge", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_drop_reasoning_phi414b_officialmodelcard_164": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." } } }, { "id": "deepinfra/deepinfra/mistralai/Mistral-Nemo-Instruct-2407", "slug": "deepinfra-deepinfra-mistralai-mistral-nemo-instruct-2407", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Mistral-Nemo-Instruct-2407", "displayName": "Mistral-Nemo-Instruct-2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": 0.04, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 4e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/mistralai/Mistral-Nemo-Instruct-2407", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-8, "output_cost_per_token": 4e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/mistralai/Mistral-Nemo-Instruct-2407" ], "manual_model_modalities_note": "Official page presents it as a text instruct model." }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "deepinfra/deepinfra/mistralai/Mistral-Small-24B-Instruct-2501", "slug": "deepinfra-deepinfra-mistralai-mistral-small-24b-instruct-2501", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Mistral-Small-24B-Instruct-2501", "displayName": "Mistral-Small-24B-Instruct-2501", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-8, "output_cost_per_token": 8e-8, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/mistralai/Mistral-Small-24B-Instruct-2501" ], "manual_model_modalities_note": "Official page describes it as a language model without multimodal support." } }, { "id": "deepinfra/deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506", "slug": "deepinfra-deepinfra-mistralai-mistral-small-3-2-24b-instruct-2506", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Mistral-Small-3.2-24B-Instruct-2506", "displayName": "Mistral-Small-3.2-24B-Instruct-2506", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 2e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/mistralai/Mistral-Small-3.2-24B-Instruct-2506" ], "manual_model_modalities_note": "Official page shows a multimodal badge and vision benchmarks." }, "benchmarks": { "mmlu_accuracy_mistralsmall3_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 81, "scoreText": "81%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mistral-small-3", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3", "exactModelOrSnapshot": "mistral-small-3", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is stated in the announcement text." } } }, { "id": "deepinfra/deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1", "slug": "deepinfra-deepinfra-mistralai-mixtral-8x7b-instruct-v0-1", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Mixtral-8x7B-Instruct-v0.1", "displayName": "Mixtral-8x7B-Instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-7, "output_cost_per_token": 4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1", "https://docs.deepinfra.com/models" ], "manual_model_modalities_note": "Official Mistral model card shows text generation; DeepInfra docs place it in the text generation category." } }, { "id": "deepinfra/deepinfra/moonshotai/Kimi-K2-Instruct", "slug": "deepinfra-deepinfra-moonshotai-kimi-k2-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Kimi-K2-Instruct", "displayName": "Kimi-K2-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/moonshotai/Kimi-K2-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000002, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/moonshotai/Kimi-K2-Instruct" ], "manual_model_modalities_note": "Official model page shows text generation." } }, { "id": "deepinfra/deepinfra/moonshotai/Kimi-K2-Instruct-0905", "slug": "deepinfra-deepinfra-moonshotai-kimi-k2-instruct-0905", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Kimi-K2-Instruct-0905", "displayName": "Kimi-K2-Instruct-0905", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.39999999999999997, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000002, "cache_read_input_token_cost": 4e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/moonshotai/Kimi-K2-Instruct-0905", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000002, "cache_read_input_token_cost": 4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905" ], "manual_model_modalities_note": "Official model page shows text generation." } }, { "id": "deepinfra/deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct", "slug": "deepinfra-deepinfra-nvidia-llama-3-1-nemotron-70b-instruct", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Llama-3.1-Nemotron-70B-Instruct", "displayName": "Llama-3.1-Nemotron-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct" ], "manual_model_modalities_note": "Official model page explicitly lists text input and text output." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "deepinfra/deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5", "slug": "deepinfra-deepinfra-nvidia-llama-3-3-nemotron-super-49b-v1-5", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "Llama-3.3-Nemotron-Super-49B-v1.5", "displayName": "Llama-3.3-Nemotron-Super-49B-v1.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://build.nvidia.com/nvidia/llama-3_3-nemotron-super-49b-v1_5", "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5" ], "manual_model_modalities_note": "Official NVIDIA and HF pages show text generation." }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "deepinfra/deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2", "slug": "deepinfra-deepinfra-nvidia-nvidia-nemotron-nano-9b-v2", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "NVIDIA-Nemotron-Nano-9B-v2", "displayName": "NVIDIA-Nemotron-Nano-9B-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.16, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 1.6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-8, "output_cost_per_token": 1.6e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2" ], "manual_model_modalities_note": "Official model page shows text generation." }, "benchmarks": { "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "deepinfra/deepinfra/openai/gpt-oss-120b", "slug": "deepinfra-deepinfra-openai-gpt-oss-120b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.44999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 4.5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/openai/gpt-oss-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-8, "output_cost_per_token": 4.5e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/openai/gpt-oss-120b", "https://status.deepinfra.com/" ], "manual_model_modalities_note": "Official model card shows text generation; DeepInfra status lists the exact model under LLM inference." }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "deepinfra/deepinfra/openai/gpt-oss-20b", "slug": "deepinfra-deepinfra-openai-gpt-oss-20b", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "gpt-oss-20b", "displayName": "gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/openai/gpt-oss-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-8, "output_cost_per_token": 1.5e-7, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://platform.openai.com/docs/models/gpt-oss-20b", "https://deepinfra.com/models/text-generation/2" ], "manual_model_modalities_note": "OpenAI docs describe the model as text-only; DeepInfra lists the exact alias under text generation." }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "deepinfra/deepinfra/zai-org/GLM-4.5", "slug": "deepinfra-deepinfra-zai-org-glm-4-5", "provider": "deepinfra", "providerSlug": "deepinfra", "name": "GLM-4.5", "displayName": "GLM-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepinfra/zai-org/GLM-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://deepinfra.com/zai-org/GLM-4.5" ], "manual_model_modalities_note": "DeepInfra exact model page serializes this alias as type text-generation." }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "deepseek/deepseek/deepseek-chat", "slug": "deepseek-deepseek-deepseek-chat", "provider": "DeepSeek", "providerSlug": "deepseek", "name": "deepseek-chat", "displayName": "deepseek-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.28, "outputUsdPer1MTokens": 0.42, "cachedInputUsdPer1MTokens": 0.028, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.28, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.8e-7, "input_cost_per_token_cache_hit": 2.8e-8, "output_cost_per_token": 4.2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-24", "shutdownDate": "2026-07-24", "earliestShutdownDate": null, "sourceUrls": [ "https://api-docs.deepseek.com/updates/" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "DeepSeek changelog says the legacy API model name deepseek-chat will be discontinued on 2026-07-24." }, "source": { "type": "litellm", "litellmKey": "deepseek/deepseek-chat", "syncedAt": "2026-05-28", "sourceUrl": "https://api-docs.deepseek.com/quick_start/pricing" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.8e-7, "input_cost_per_token_cache_hit": 2.8e-8, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-7, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://api-docs.deepseek.com/updates/" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "DeepSeek changelog says the legacy API model name deepseek-chat will be discontinued on 2026-07-24." } }, { "id": "deepseek/deepseek/deepseek-coder", "slug": "deepseek-deepseek-deepseek-coder", "provider": "DeepSeek", "providerSlug": "deepseek", "name": "deepseek-coder", "displayName": "deepseek-coder", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.14, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": 0.014, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.14, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.4e-7, "input_cost_per_token_cache_hit": 1.4e-8, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepseek/deepseek-coder", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.4e-7, "input_cost_per_token_cache_hit": 1.4e-8, "litellm_provider": "deepseek", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-7, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "deepseek/deepseek/deepseek-r1", "slug": "deepseek-deepseek-deepseek-r1", "provider": "DeepSeek", "providerSlug": "deepseek", "name": "deepseek-r1", "displayName": "deepseek-r1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.55, "outputUsdPer1MTokens": 2.1900000000000004, "cachedInputUsdPer1MTokens": 0.14, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.55, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-7, "input_cost_per_token_cache_hit": 1.4e-7, "output_cost_per_token": 0.00000219 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65536, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepseek/deepseek-r1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5.5e-7, "input_cost_per_token_cache_hit": 1.4e-7, "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000219, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "deepseek/deepseek/deepseek-reasoner", "slug": "deepseek-deepseek-deepseek-reasoner", "provider": "DeepSeek", "providerSlug": "deepseek", "name": "deepseek-reasoner", "displayName": "deepseek-reasoner", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.28, "outputUsdPer1MTokens": 0.42, "cachedInputUsdPer1MTokens": 0.028, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.28, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.8e-7, "input_cost_per_token_cache_hit": 2.8e-8, "output_cost_per_token": 4.2e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 131072, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": false, "native_streaming": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-24", "shutdownDate": "2026-07-24", "earliestShutdownDate": null, "sourceUrls": [ "https://api-docs.deepseek.com/updates/" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "DeepSeek changelog says the legacy API model name deepseek-reasoner will be discontinued on 2026-07-24." }, "source": { "type": "litellm", "litellmKey": "deepseek/deepseek-reasoner", "syncedAt": "2026-05-28", "sourceUrl": "https://api-docs.deepseek.com/quick_start/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.8e-7, "input_cost_per_token_cache_hit": 2.8e-8, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-7, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://api-docs.deepseek.com/updates/" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "DeepSeek changelog says the legacy API model name deepseek-reasoner will be discontinued on 2026-07-24." } }, { "id": "deepseek/deepseek/deepseek-v3", "slug": "deepseek-deepseek-deepseek-v3", "provider": "DeepSeek", "providerSlug": "deepseek", "name": "deepseek-v3", "displayName": "deepseek-v3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 1.1, "cachedInputUsdPer1MTokens": 0.07, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 7e-8, "input_cost_per_token": 2.7e-7, "input_cost_per_token_cache_hit": 7e-8, "output_cost_per_token": 0.0000011 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65536, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepseek/deepseek-v3", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 7e-8, "input_cost_per_token": 2.7e-7, "input_cost_per_token_cache_hit": 7e-8, "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000011, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "deepseek/deepseek/deepseek-v3.2", "slug": "deepseek-deepseek-deepseek-v3-2", "provider": "DeepSeek", "providerSlug": "deepseek", "name": "deepseek-v3.2", "displayName": "deepseek-v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.28, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.028, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.28, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.8e-7, "input_cost_per_token_cache_hit": 2.8e-8, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepseek/deepseek-v3.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.8e-7, "input_cost_per_token_cache_hit": 2.8e-8, "litellm_provider": "deepseek", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 4e-7, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock_converse/deepseek.v3-v1:0", "slug": "bedrock_converse-deepseek-v3-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "deepseek.v3-v1:0", "displayName": "deepseek.v3-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.58, "outputUsdPer1MTokens": 1.68, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.58, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.8e-7, "output_cost_per_token": 0.00000168 } }, "limits": { "contextWindow": 81920, "maxInputTokens": 163840, "maxOutputTokens": 81920, "maxTokens": 81920, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "native_structured_output": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepseek.v3-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5.8e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 81920, "max_tokens": 81920, "mode": "chat", "output_cost_per_token": 0.00000168, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html" ], "manual_model_modalities_note": "Bedrock Converse exact DeepSeek route id from official docs" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "bedrock_converse/deepseek.v3.2", "slug": "bedrock_converse-deepseek-v3-2", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "deepseek.v3.2", "displayName": "deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.62, "outputUsdPer1MTokens": 1.85, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.62, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepseek.v3.2", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6.2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000185, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" ], "manual_model_modalities_note": "Bedrock Converse exact DeepSeek route id from official docs" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "nlp_cloud/dolphin", "slug": "nlp_cloud-dolphin", "provider": "nlp_cloud", "providerSlug": "nlp_cloud", "name": "dolphin", "displayName": "dolphin", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "dolphin", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "completion", "output_cost_per_token": 5e-7 } }, { "id": "volcengine/deepseek-v3-2-251201", "slug": "volcengine-deepseek-v3-2-251201", "provider": "volcengine", "providerSlug": "volcengine", "name": "deepseek-v3-2-251201", "displayName": "deepseek-v3-2-251201", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 98304, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deepseek-v3-2-251201", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "volcengine", "max_input_tokens": 98304, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "volcengine/glm-4-7-251222", "slug": "volcengine-glm-4-7-251222", "provider": "volcengine", "providerSlug": "volcengine", "name": "glm-4-7-251222", "displayName": "glm-4-7-251222", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 204800, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "glm-4-7-251222", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "volcengine", "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "volcengine/kimi-k2-thinking-251104", "slug": "volcengine-kimi-k2-thinking-251104", "provider": "volcengine", "providerSlug": "volcengine", "name": "kimi-k2-thinking-251104", "displayName": "kimi-k2-thinking-251104", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 229376, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "kimi-k2-thinking-251104", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "volcengine", "max_input_tokens": 229376, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "volcengine/doubao-embedding", "slug": "volcengine-doubao-embedding", "provider": "volcengine", "providerSlug": "volcengine", "name": "doubao-embedding", "displayName": "doubao-embedding", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": null, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 2560, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "doubao-embedding", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "volcengine", "max_input_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" }, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 2560 } }, { "id": "volcengine/doubao-embedding-large", "slug": "volcengine-doubao-embedding-large", "provider": "volcengine", "providerSlug": "volcengine", "name": "doubao-embedding-large", "displayName": "doubao-embedding-large", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": null, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 2048, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "doubao-embedding-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "volcengine", "max_input_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" }, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 2048 } }, { "id": "volcengine/doubao-embedding-large-text-240915", "slug": "volcengine-doubao-embedding-large-text-240915", "provider": "volcengine", "providerSlug": "volcengine", "name": "doubao-embedding-large-text-240915", "displayName": "doubao-embedding-large-text-240915", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": null, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 4096, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "doubao-embedding-large-text-240915", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "volcengine", "max_input_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" }, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 4096 } }, { "id": "volcengine/doubao-embedding-large-text-250515", "slug": "volcengine-doubao-embedding-large-text-250515", "provider": "volcengine", "providerSlug": "volcengine", "name": "doubao-embedding-large-text-250515", "displayName": "doubao-embedding-large-text-250515", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": null, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 2048, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "doubao-embedding-large-text-250515", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "volcengine", "max_input_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" }, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 2048 } }, { "id": "volcengine/doubao-embedding-text-240715", "slug": "volcengine-doubao-embedding-text-240715", "provider": "volcengine", "providerSlug": "volcengine", "name": "doubao-embedding-text-240715", "displayName": "doubao-embedding-text-240715", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": null, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 2560, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "doubao-embedding-text-240715", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "volcengine", "max_input_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" }, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 2560 }, "benchmarks": { "local_mgteretrievaltable_avg_gtemultilingualbasedense_paper_344": { "label": "mGTE retrieval table", "category": "long_context", "score": 66.7, "scoreText": "66.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Dense", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_gtemultilingualbasesparse_paper_345": { "label": "mGTE retrieval table", "category": "long_context", "score": 57.2, "scoreText": "57.2", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Sparse", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_gtemultilingualbasedensesparse_paper_346": { "label": "mGTE retrieval table", "category": "long_context", "score": 68.9, "scoreText": "68.9", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Dense + Sparse", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "exa_ai/exa_ai/search", "slug": "exa_ai-exa_ai-search", "provider": "exa_ai", "providerSlug": "exa_ai", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "exa_ai/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "exa_ai", "mode": "search", "tiered_pricing": [ { "input_cost_per_query": 0.005, "max_results_range": [ 0, 25 ] }, { "input_cost_per_query": 0.025, "max_results_range": [ 26, 100 ] } ], "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "firecrawl/firecrawl/search", "slug": "firecrawl-firecrawl-search", "provider": "firecrawl", "providerSlug": "firecrawl", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "firecrawl/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "firecrawl", "mode": "search", "tiered_pricing": [ { "input_cost_per_query": 0.00166, "max_results_range": [ 1, 10 ] }, { "input_cost_per_query": 0.00332, "max_results_range": [ 11, 20 ] }, { "input_cost_per_query": 0.00498, "max_results_range": [ 21, 30 ] }, { "input_cost_per_query": 0.00664, "max_results_range": [ 31, 40 ] }, { "input_cost_per_query": 0.0083, "max_results_range": [ 41, 50 ] }, { "input_cost_per_query": 0.00996, "max_results_range": [ 51, 60 ] }, { "input_cost_per_query": 0.01162, "max_results_range": [ 61, 70 ] }, { "input_cost_per_query": 0.01328, "max_results_range": [ 71, 80 ] }, { "input_cost_per_query": 0.01494, "max_results_range": [ 81, 90 ] }, { "input_cost_per_query": 0.0166, "max_results_range": [ 91, 100 ] } ], "metadata": { "notes": "Firecrawl search pricing: $83 for 100,000 credits, 2 credits per 10 results. Cost = ceiling(limit/10) * 2 * $0.00083" }, "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "perplexity/perplexity/search", "slug": "perplexity-perplexity-search", "provider": "perplexity", "providerSlug": "perplexity", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 5, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.005, "litellm_provider": "perplexity", "mode": "search", "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "searxng/searxng/search", "slug": "searxng-searxng-search", "provider": "searxng", "providerSlug": "searxng", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "searxng/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "searxng", "mode": "search", "input_cost_per_query": 0, "metadata": { "notes": "SearXNG is an open-source metasearch engine. Free to use when self-hosted or using public instances." }, "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "serper/serper/search", "slug": "serper-serper-search", "provider": "serper", "providerSlug": "serper", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 1, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "serper/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.001, "litellm_provider": "serper", "mode": "search", "metadata": { "notes": "Serper Google Search API. Pricing: $1.00/1k queries (Starter), $0.75/1k (Standard), $0.50/1k (Scale), $0.30/1k (Ultimate)." }, "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "elevenlabs/elevenlabs/scribe_v1", "slug": "elevenlabs-elevenlabs-scribe_v1", "provider": "elevenlabs", "providerSlug": "elevenlabs", "name": "scribe_v1", "displayName": "scribe_v1", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0000611, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0000611, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "elevenlabs/scribe_v1", "syncedAt": "2026-05-28", "sourceUrl": "https://elevenlabs.io/pricing" }, "rawLitellm": { "input_cost_per_second": 0.0000611, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", "notes": "ElevenLabs Scribe v1 - state-of-the-art speech recognition model with 99 language support", "original_pricing_per_hour": 0.22 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://elevenlabs.io/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "elevenlabs/elevenlabs/scribe_v1_experimental", "slug": "elevenlabs-elevenlabs-scribe_v1_experimental", "provider": "elevenlabs", "providerSlug": "elevenlabs", "name": "scribe_v1_experimental", "displayName": "scribe_v1_experimental", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0000611, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0000611, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "elevenlabs/scribe_v1_experimental", "syncedAt": "2026-05-28", "sourceUrl": "https://elevenlabs.io/pricing" }, "rawLitellm": { "input_cost_per_second": 0.0000611, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", "notes": "ElevenLabs Scribe v1 experimental - enhanced version of the main Scribe model", "original_pricing_per_hour": 0.22 }, "mode": "audio_transcription", "output_cost_per_second": 0, "source": "https://elevenlabs.io/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "elevenlabs/elevenlabs/eleven_v3", "slug": "elevenlabs-elevenlabs-eleven_v3", "provider": "elevenlabs", "providerSlug": "elevenlabs", "name": "eleven_v3", "displayName": "eleven_v3", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00018, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00018 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "elevenlabs/eleven_v3", "syncedAt": "2026-05-28", "sourceUrl": "https://elevenlabs.io/pricing" }, "rawLitellm": { "input_cost_per_character": 0.00018, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.18/1000 characters (Scale plan pricing, 1 credit per character)", "notes": "ElevenLabs Eleven v3 - most expressive TTS model with 70+ languages and audio tags support" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "elevenlabs/elevenlabs/eleven_multilingual_v2", "slug": "elevenlabs-elevenlabs-eleven_multilingual_v2", "provider": "elevenlabs", "providerSlug": "elevenlabs", "name": "eleven_multilingual_v2", "displayName": "eleven_multilingual_v2", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00018, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00018 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "elevenlabs/eleven_multilingual_v2", "syncedAt": "2026-05-28", "sourceUrl": "https://elevenlabs.io/pricing" }, "rawLitellm": { "input_cost_per_character": 0.00018, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.18/1000 characters (Scale plan pricing, 1 credit per character)", "notes": "ElevenLabs Eleven Multilingual v2 - default TTS model with 29 languages support" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "cohere/embed-english-light-v2.0", "slug": "cohere-embed-english-light-v2-0", "provider": "Cohere", "providerSlug": "cohere", "name": "embed-english-light-v2.0", "displayName": "embed-english-light-v2.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-04-04", "shutdownDate": "2026-04-04", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.cohere.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "embed-english-light-v2.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "cohere", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "embedding", "output_cost_per_token": 0, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.cohere.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "cohere/embed-english-light-v3.0", "slug": "cohere-embed-english-light-v3-0", "provider": "Cohere", "providerSlug": "cohere", "name": "embed-english-light-v3.0", "displayName": "embed-english-light-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "embed-english-light-v3.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "cohere", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "cohere/embed-english-v2.0", "slug": "cohere-embed-english-v2-0", "provider": "Cohere", "providerSlug": "cohere", "name": "embed-english-v2.0", "displayName": "embed-english-v2.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": null, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-04-04", "shutdownDate": "2026-04-04", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.cohere.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "embed-english-v2.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.cohere.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "cohere/embed-english-v3.0", "slug": "cohere-embed-english-v3-0", "provider": "Cohere", "providerSlug": "cohere", "name": "embed-english-v3.0", "displayName": "embed-english-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 100, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0001, "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true, "image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "embed-english-v3.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.0001, "input_cost_per_token": 1e-7, "litellm_provider": "cohere", "max_input_tokens": 1024, "max_tokens": 1024, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, "mode": "embedding", "output_cost_per_token": 0, "supports_embedding_image_input": true, "supports_image_input": true } }, { "id": "cohere/embed-multilingual-v2.0", "slug": "cohere-embed-multilingual-v2-0", "provider": "Cohere", "providerSlug": "cohere", "name": "embed-multilingual-v2.0", "displayName": "embed-multilingual-v2.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 768, "maxInputTokens": 768, "maxOutputTokens": null, "maxTokens": 768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-04-04", "shutdownDate": "2026-04-04", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.cohere.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "embed-multilingual-v2.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "cohere", "max_input_tokens": 768, "max_tokens": 768, "mode": "embedding", "output_cost_per_token": 0, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.cohere.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "cohere/embed-multilingual-v3.0", "slug": "cohere-embed-multilingual-v3-0", "provider": "Cohere", "providerSlug": "cohere", "name": "embed-multilingual-v3.0", "displayName": "embed-multilingual-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "embed-multilingual-v3.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "cohere", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "embedding", "output_cost_per_token": 0, "supports_embedding_image_input": true } }, { "id": "cohere/embed-multilingual-light-v3.0", "slug": "cohere-embed-multilingual-light-v3-0", "provider": "Cohere", "providerSlug": "cohere", "name": "embed-multilingual-light-v3.0", "displayName": "embed-multilingual-light-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 100, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 100, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0001, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "embed-multilingual-light-v3.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0001, "litellm_provider": "cohere", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "embedding", "output_cost_per_token": 0, "supports_embedding_image_input": true } }, { "id": "bedrock_converse/eu.amazon.nova-lite-v1:0", "slug": "bedrock_converse-eu-amazon-nova-lite-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.amazon.nova-lite-v1:0", "displayName": "eu.amazon.nova-lite-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.078, "outputUsdPer1MTokens": 0.312, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.078, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.8e-8, "output_cost_per_token": 3.12e-7 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.amazon.nova-lite-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.8e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.12e-7, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-lite.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock_converse/eu.amazon.nova-micro-v1:0", "slug": "bedrock_converse-eu-amazon-nova-micro-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.amazon.nova-micro-v1:0", "displayName": "eu.amazon.nova-micro-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.046, "outputUsdPer1MTokens": 0.184, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.046, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.6e-8, "output_cost_per_token": 1.84e-7 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 128000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.amazon.nova-micro-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4.6e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.84e-7, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-micro.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock_converse/eu.amazon.nova-pro-v1:0", "slug": "bedrock_converse-eu-amazon-nova-pro-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.amazon.nova-pro-v1:0", "displayName": "eu.amazon.nova-pro-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.0499999999999998, "outputUsdPer1MTokens": 4.199999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.0499999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000105, "output_cost_per_token": 0.0000042 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.amazon.nova-pro-v1:0", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 0.00000105, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 0.0000042, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-pro.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock/eu.anthropic.claude-3-5-haiku-20241022-v1:0", "slug": "bedrock-eu-anthropic-claude-3-5-haiku-20241022-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.anthropic.claude-3-5-haiku-20241022-v1:0", "displayName": "eu.anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": 0.3125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-3-5-haiku-20241022-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-5-haiku.html" ], "manual_model_modalities_note": "Bedrock exact EU geo-inference alias from official docs." }, "benchmarks": { "aidercodeeditingleaderboard_score_claude35haiku20241022_benchmarkleaderboard_68": { "label": "Aider Code Editing", "category": "coding", "score": 75.2, "scoreText": "75.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Haiku", "exactModelOrSnapshot": "claude-3-5-haiku-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." } } }, { "id": "bedrock_converse/eu.anthropic.claude-haiku-4-5-20251001-v1:0", "slug": "bedrock_converse-eu-anthropic-claude-haiku-4-5-20251001-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 5.5, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": 1.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000001375, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000055 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-10-15" }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000001375, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 0.0000011, "deprecation_date": "2026-10-15", "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000055, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock/eu.anthropic.claude-3-5-sonnet-20240620-v1:0", "slug": "bedrock-eu-anthropic-claude-3-5-sonnet-20240620-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0", "displayName": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "https://docs.aws.amazon.com/id_id/bedrock/latest/userguide/inference-profiles-support.html" ], "manual_model_modalities_note": "Bedrock exact EU inference-profile alias from official docs." }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/eu.anthropic.claude-3-5-sonnet-20241022-v2:0", "slug": "bedrock-eu-anthropic-claude-3-5-sonnet-20241022-v2-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0", "displayName": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact EU geo-inference alias from official docs." }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/eu.anthropic.claude-3-7-sonnet-20250219-v1:0", "slug": "bedrock-eu-anthropic-claude-3-7-sonnet-20250219-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0", "displayName": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact EU inference-profile alias from official docs." }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/eu.anthropic.claude-3-haiku-20240307-v1:0", "slug": "bedrock-eu-anthropic-claude-3-haiku-20240307-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.anthropic.claude-3-haiku-20240307-v1:0", "displayName": "eu.anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": 0.3125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-3-haiku-20240307-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.html" ], "manual_model_modalities_note": "Bedrock exact EU geo-inference alias from official docs." } }, { "id": "bedrock/eu.anthropic.claude-3-opus-20240229-v1:0", "slug": "bedrock-eu-anthropic-claude-3-opus-20240229-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.anthropic.claude-3-opus-20240229-v1:0", "displayName": "eu.anthropic.claude-3-opus-20240229-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "cache_read_input_token_cost": 0.0000015, "cache_creation_input_token_cost": 0.00001875 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-3-opus-20240229-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000075, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 0.0000015, "cache_creation_input_token_cost": 0.00001875, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact EU inference-profile alias from official docs." }, "benchmarks": { "aiderrefactoringleaderboard_score_claude3opus20240229_benchmarkleaderboard_69": { "label": "Aider Refactoring", "category": "coding", "score": 72.3, "scoreText": "72.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/refactor.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3 Opus", "exactModelOrSnapshot": "claude-3-opus-20240229", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Refactoring leaderboard row; diff edit format." } } }, { "id": "bedrock/eu.anthropic.claude-3-sonnet-20240229-v1:0", "slug": "bedrock-eu-anthropic-claude-3-sonnet-20240229-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.anthropic.claude-3-sonnet-20240229-v1:0", "displayName": "eu.anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-3-sonnet-20240229-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el" ], "manual_model_modalities_note": "Bedrock exact EU inference-profile alias from official docs." } }, { "id": "bedrock_converse/eu.anthropic.claude-opus-4-1-20250805-v1:0", "slug": "bedrock_converse-eu-anthropic-claude-opus-4-1-20250805-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.anthropic.claude-opus-4-1-20250805-v1:0", "displayName": "eu.anthropic.claude-opus-4-1-20250805-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-opus-4-1-20250805-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-1.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "bedrock_converse/eu.anthropic.claude-opus-4-20250514-v1:0", "slug": "bedrock_converse-eu-anthropic-claude-opus-4-20250514-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.anthropic.claude-opus-4-20250514-v1:0", "displayName": "eu.anthropic.claude-opus-4-20250514-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-opus-4-20250514-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "bedrock_converse/eu.anthropic.claude-sonnet-4-20250514-v1:0", "slug": "bedrock_converse-eu-anthropic-claude-sonnet-4-20250514-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.anthropic.claude-sonnet-4-20250514-v1:0", "displayName": "eu.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-sonnet-4-20250514-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "bedrock_converse/eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock_converse-eu-anthropic-claude-sonnet-4-5-20250929-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6.6000000000000005, "above200kOutputUsdPer1MTokens": 24.75, "above200kCachedInputUsdPer1MTokens": 0.66, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/eu.meta.llama3-2-1b-instruct-v1:0", "slug": "bedrock-eu-meta-llama3-2-1b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.meta.llama3-2-1b-instruct-v1:0", "displayName": "eu.meta.llama3-2-1b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.13, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 1.3e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.meta.llama3-2-1b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.3e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.3e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact EU geo-inference alias from official docs." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "bedrock/eu.meta.llama3-2-3b-instruct-v1:0", "slug": "bedrock-eu-meta-llama3-2-3b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "eu.meta.llama3-2-3b-instruct-v1:0", "displayName": "eu.meta.llama3-2-3b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19, "outputUsdPer1MTokens": 0.19, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.9e-7, "output_cost_per_token": 1.9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.meta.llama3-2-3b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.9e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.9e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact EU geo-inference alias from official docs." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "bedrock_converse/eu.mistral.pixtral-large-2502-v1:0", "slug": "bedrock_converse-eu-mistral-pixtral-large-2502-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.mistral.pixtral-large-2502-v1:0", "displayName": "eu.mistral.pixtral-large-2502-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "image", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.mistral.pixtral-large-2502-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000006, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-pixtral-large-2502.html" ], "manual_model_modalities_note": "Bedrock Converse exact Mistral route id from official docs" } }, { "id": "fal_ai/fal_ai/bria/text-to-image/3.2", "slug": "fal_ai-fal_ai-bria-text-to-image-3-2", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "3.2", "displayName": "3.2", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 39800, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.0398 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/bria/text-to-image/3.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/flux-pro/v1.1", "slug": "fal_ai-fal_ai-fal-ai-flux-pro-v1-1", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "v1.1", "displayName": "v1.1", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/flux-pro/v1.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/flux-pro/v1.1-ultra", "slug": "fal_ai-fal_ai-fal-ai-flux-pro-v1-1-ultra", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "v1.1-ultra", "displayName": "v1.1-ultra", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/flux-pro/v1.1-ultra", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/flux/schnell", "slug": "fal_ai-fal_ai-fal-ai-flux-schnell", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "schnell", "displayName": "schnell", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 3000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/flux/schnell", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.003, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/bytedance/seedream/v3/text-to-image", "slug": "fal_ai-fal_ai-fal-ai-bytedance-seedream-v3-text-to-image", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "text-to-image", "displayName": "text-to-image", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 30000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.03 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/bytedance/seedream/v3/text-to-image", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/bytedance/dreamina/v3.1/text-to-image", "slug": "fal_ai-fal_ai-fal-ai-bytedance-dreamina-v3-1-text-to-image", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "text-to-image", "displayName": "text-to-image", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 30000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.03 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/bytedance/dreamina/v3.1/text-to-image", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/ideogram/v3", "slug": "fal_ai-fal_ai-fal-ai-ideogram-v3", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "ideogram", "displayName": "ideogram", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/ideogram/v3", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/imagen4/preview", "slug": "fal_ai-fal_ai-fal-ai-imagen4-preview", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "preview", "displayName": "preview", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 39800, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.0398 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/imagen4/preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/imagen4/preview/fast", "slug": "fal_ai-fal_ai-fal-ai-imagen4-preview-fast", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "fast", "displayName": "fast", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 20000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.02 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/imagen4/preview/fast", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.02, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/imagen4/preview/ultra", "slug": "fal_ai-fal_ai-fal-ai-imagen4-preview-ultra", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "ultra", "displayName": "ultra", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/imagen4/preview/ultra", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/recraft/v3/text-to-image", "slug": "fal_ai-fal_ai-fal-ai-recraft-v3-text-to-image", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "text-to-image", "displayName": "text-to-image", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 39800, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.0398 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/recraft/v3/text-to-image", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "fal_ai/fal_ai/fal-ai/stable-diffusion-v35-medium", "slug": "fal_ai-fal_ai-fal-ai-stable-diffusion-v35-medium", "provider": "fal_ai", "providerSlug": "fal_ai", "name": "stable-diffusion-v35-medium", "displayName": "stable-diffusion-v35-medium", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 39800, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.0398 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fal_ai/fal-ai/stable-diffusion-v35-medium", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "featherless_ai/featherless_ai/featherless-ai/Qwerky-72B", "slug": "featherless_ai-featherless_ai-featherless-ai-qwerky-72b", "provider": "featherless_ai", "providerSlug": "featherless_ai", "name": "Qwerky-72B", "displayName": "Qwerky-72B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "featherless_ai/featherless-ai/Qwerky-72B", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat" } }, { "id": "featherless_ai/featherless_ai/featherless-ai/Qwerky-QwQ-32B", "slug": "featherless_ai-featherless_ai-featherless-ai-qwerky-qwq-32b", "provider": "featherless_ai", "providerSlug": "featherless_ai", "name": "Qwerky-QwQ-32B", "displayName": "Qwerky-QwQ-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "featherless_ai/featherless-ai/Qwerky-QwQ-32B", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat" } }, { "id": "fireworks_ai/fireworks-ai-4.1b-to-16b", "slug": "fireworks_ai-fireworks-ai-4-1b-to-16b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "fireworks-ai-4.1b-to-16b", "displayName": "fireworks-ai-4.1b-to-16b", "mode": "unknown", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks-ai-4.1b-to-16b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "output_cost_per_token": 2e-7 } }, { "id": "fireworks_ai/fireworks-ai-56b-to-176b", "slug": "fireworks_ai-fireworks-ai-56b-to-176b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "fireworks-ai-56b-to-176b", "displayName": "fireworks-ai-56b-to-176b", "mode": "unknown", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks-ai-56b-to-176b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "output_cost_per_token": 0.0000012 } }, { "id": "fireworks_ai/fireworks-ai-above-16b", "slug": "fireworks_ai-fireworks-ai-above-16b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "fireworks-ai-above-16b", "displayName": "fireworks-ai-above-16b", "mode": "unknown", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks-ai-above-16b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "output_cost_per_token": 9e-7 } }, { "id": "fireworks_ai/fireworks-ai-default", "slug": "fireworks_ai-fireworks-ai-default", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "fireworks-ai-default", "displayName": "fireworks-ai-default", "mode": "unknown", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks-ai-default", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "fireworks_ai", "output_cost_per_token": 0 } }, { "id": "fireworks_ai-embedding-models/fireworks-ai-embedding-150m-to-350m", "slug": "fireworks_ai-embedding-models-fireworks-ai-embedding-150m-to-350m", "provider": "fireworks_ai-embedding-models", "providerSlug": "fireworks_ai-embedding-models", "name": "fireworks-ai-embedding-150m-to-350m", "displayName": "fireworks-ai-embedding-150m-to-350m", "mode": "unknown", "pricing": { "inputUsdPer1MTokens": 0.016, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.016, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.6e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks-ai-embedding-150m-to-350m", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.6e-8, "litellm_provider": "fireworks_ai-embedding-models", "output_cost_per_token": 0 } }, { "id": "fireworks_ai-embedding-models/fireworks-ai-embedding-up-to-150m", "slug": "fireworks_ai-embedding-models-fireworks-ai-embedding-up-to-150m", "provider": "fireworks_ai-embedding-models", "providerSlug": "fireworks_ai-embedding-models", "name": "fireworks-ai-embedding-up-to-150m", "displayName": "fireworks-ai-embedding-up-to-150m", "mode": "unknown", "pricing": { "inputUsdPer1MTokens": 0.008, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.008, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-9, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks-ai-embedding-up-to-150m", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-9, "litellm_provider": "fireworks_ai-embedding-models", "output_cost_per_token": 0 } }, { "id": "fireworks_ai/fireworks-ai-moe-up-to-56b", "slug": "fireworks_ai-fireworks-ai-moe-up-to-56b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "fireworks-ai-moe-up-to-56b", "displayName": "fireworks-ai-moe-up-to-56b", "mode": "unknown", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks-ai-moe-up-to-56b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "output_cost_per_token": 5e-7 } }, { "id": "fireworks_ai/fireworks-ai-up-to-4b", "slug": "fireworks_ai-fireworks-ai-up-to-4b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "fireworks-ai-up-to-4b", "displayName": "fireworks-ai-up-to-4b", "mode": "unknown", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks-ai-up-to-4b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "output_cost_per_token": 2e-7 } }, { "id": "fireworks_ai-embedding-models/fireworks_ai/WhereIsAI/UAE-Large-V1", "slug": "fireworks_ai-embedding-models-fireworks_ai-whereisai-uae-large-v1", "provider": "fireworks_ai-embedding-models", "providerSlug": "fireworks_ai-embedding-models", "name": "UAE-Large-V1", "displayName": "UAE-Large-V1", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.016, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.016, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.6e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/WhereIsAI/UAE-Large-V1", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1.6e-8, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "source": "https://fireworks.ai/pricing" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-coder-v2-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-coder-v2-instruct", "displayName": "deepseek-coder-v2-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-coder-v2-instruct" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-r1", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-r1", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-r1", "displayName": "deepseek-r1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 20480, "maxInputTokens": 128000, "maxOutputTokens": 20480, "maxTokens": 20480, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-r1", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 20480, "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 0.000008, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-r1" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-r1-0528", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-r1-0528", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-r1-0528", "displayName": "deepseek-r1-0528", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 160000, "maxInputTokens": 160000, "maxOutputTokens": 160000, "maxTokens": 160000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "fireworks_ai", "max_input_tokens": 160000, "max_output_tokens": 160000, "max_tokens": 160000, "mode": "chat", "output_cost_per_token": 0.000008, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-r1-0528" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-r1-basic", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-r1-basic", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-r1-basic", "displayName": "deepseek-r1-basic", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.55, "outputUsdPer1MTokens": 2.1900000000000004, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.55, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219 } }, "limits": { "contextWindow": 20480, "maxInputTokens": 128000, "maxOutputTokens": 20480, "maxTokens": 20480, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 5.5e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 20480, "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 0.00000219, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-r1-basic" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-v3", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-v3", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-v3", "displayName": "deepseek-v3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-v3", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-7, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-v3" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-v3-0324", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-v3-0324", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-v3-0324", "displayName": "deepseek-v3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/models/fireworks/deepseek-v3-0324" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 9e-7, "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-v3-0324" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-v3p1", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-v3p1", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-v3p1", "displayName": "deepseek-v3p1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.56, "outputUsdPer1MTokens": 1.68, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.56, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.6e-7, "output_cost_per_token": 0.00000168 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.fireworks.ai/updates/changelog" ], "checkedAt": "2026-06-02", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Fireworks changelog says serverless DeepSeek V3.1 was removed on May 14, 2026; mapped to the exact Fireworks model slug by naming convention." }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-v3p1", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 5.6e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000168, "source": "https://fireworks.ai/pricing", "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.fireworks.ai/guides/querying-text-models", "https://docs.fireworks.ai/getting-started/quickstart" ], "manual_model_modalities_note": "Fireworks exact route id from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.fireworks.ai/updates/changelog" ], "manual_model_lifecycle_checked_at": "2026-06-02", "manual_model_lifecycle_note": "Fireworks changelog says serverless DeepSeek V3.1 was removed on May 14, 2026; mapped to the exact Fireworks model slug by naming convention." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-v3p1-terminus", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-v3p1-terminus", "displayName": "deepseek-v3p1-terminus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.56, "outputUsdPer1MTokens": 1.68, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.56, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.6e-7, "output_cost_per_token": 0.00000168 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 5.6e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000168, "source": "https://fireworks.ai/pricing", "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/deepseek-ai/deepseek-v3p1-terminus" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-v3p2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-v3p2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-v3p2", "displayName": "deepseek-v3p2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.56, "outputUsdPer1MTokens": 1.68, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.56, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.6e-7, "output_cost_per_token": 0.00000168 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.fireworks.ai/updates/changelog" ], "checkedAt": "2026-06-02", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Fireworks changelog says serverless DeepSeek V3.2 was removed on May 14, 2026; mapped to the exact Fireworks model slug by naming convention." }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-v3p2", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/models/fireworks/deepseek-v3p2" }, "rawLitellm": { "input_cost_per_token": 5.6e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000168, "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.fireworks.ai/getting-started/quickstart", "https://docs.fireworks.ai/api-reference/post-chatcompletions" ], "manual_model_modalities_note": "Fireworks exact route id from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.fireworks.ai/updates/changelog" ], "manual_model_lifecycle_checked_at": "2026-06-02", "manual_model_lifecycle_note": "Fireworks changelog says serverless DeepSeek V3.2 was removed on May 14, 2026; mapped to the exact Fireworks model slug by naming convention." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/firefunction-v2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-firefunction-v2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "firefunction-v2", "displayName": "firefunction-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/firefunction-v2", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-7, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/firefunction-v2" ], "manual_model_modalities_note": "Official model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/glm-4p5", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-glm-4p5", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "glm-4p5", "displayName": "glm-4p5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.55, "outputUsdPer1MTokens": 2.1900000000000004, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.55, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219 } }, "limits": { "contextWindow": 96000, "maxInputTokens": 128000, "maxOutputTokens": 96000, "maxTokens": 96000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/glm-4p5", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/models/fireworks/glm-4p5" }, "rawLitellm": { "input_cost_per_token": 5.5e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 96000, "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 0.00000219, "source": "https://fireworks.ai/models/fireworks/glm-4p5", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.fireworks.ai/guides/querying-embeddings-models", "https://docs.fireworks.ai/api-reference/post-completions" ], "manual_model_modalities_note": "Fireworks exact route id from official docs" }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/glm-4p5-air", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-glm-4p5-air", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "glm-4p5-air", "displayName": "glm-4p5-air", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": 96000, "maxInputTokens": 128000, "maxOutputTokens": 96000, "maxTokens": 96000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/glm-4p5-air", "syncedAt": "2026-05-28", "sourceUrl": "https://artificialanalysis.ai/models/glm-4-5-air" }, "rawLitellm": { "input_cost_per_token": 2.2e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 96000, "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 8.8e-7, "source": "https://artificialanalysis.ai/models/glm-4-5-air", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/glm-4p5-air" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/glm-4p6", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-glm-4p6", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "glm-4p6", "displayName": "glm-4p6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.55, "outputUsdPer1MTokens": 2.1900000000000004, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.55, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219 } }, "limits": { "contextWindow": 202800, "maxInputTokens": 202800, "maxOutputTokens": 202800, "maxTokens": 202800, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/glm-4p6", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219, "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/glm-4p6" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/glm-4p7", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-glm-4p7", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "glm-4p7", "displayName": "glm-4p7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 202800, "maxInputTokens": 202800, "maxOutputTokens": 202800, "maxTokens": 202800, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.fireworks.ai/updates/changelog" ], "checkedAt": "2026-06-02", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Fireworks changelog says serverless GLM 4.7 was removed on May 14, 2026; mapped to the exact Fireworks model slug by naming convention." }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/glm-4p7", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/models/fireworks/glm-4p7" }, "rawLitellm": { "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 0.0000022, "source": "https://fireworks.ai/models/fireworks/glm-4p7", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/glm-4p7" ], "manual_model_modalities_note": "Fireworks exact route id from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.fireworks.ai/updates/changelog" ], "manual_model_lifecycle_checked_at": "2026-06-02", "manual_model_lifecycle_note": "Fireworks changelog says serverless GLM 4.7 was removed on May 14, 2026; mapped to the exact Fireworks model slug by naming convention." }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/glm-5p1", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-glm-5p1", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "glm-5p1", "displayName": "glm-5p1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.4, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.26, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.6e-7, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 202800, "maxInputTokens": 202800, "maxOutputTokens": 202800, "maxTokens": 202800, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "reasoning": true, "response_schema": false, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/glm-5p1", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/models/fireworks/glm-5p1" }, "rawLitellm": { "cache_read_input_token_cost": 2.6e-7, "input_cost_per_token": 0.0000014, "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 0.0000044, "source": "https://fireworks.ai/models/fireworks/glm-5p1", "supports_function_calling": false, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/glm-5p1" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "hle_score_glm5_officialmodelcard_165": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 30.5, "scoreText": "30.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "gpqadiamond_score_glm5_officialmodelcard_166": { "label": "GPQA Diamond", "category": "reasoning", "score": 86, "scoreText": "86.0", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchverified_score_glm5_officialmodelcard_167": { "label": "SWE-bench Verified", "category": "coding", "score": 77.8, "scoreText": "77.8", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/gpt-oss-120b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-gpt-oss-120b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/gpt-oss-120b", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/gpt-oss-120b" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/gpt-oss-20b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-gpt-oss-20b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "gpt-oss-20b", "displayName": "gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/gpt-oss-20b", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/gpt-oss-20b" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/kimi-k2-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-kimi-k2-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "kimi-k2-instruct", "displayName": "kimi-k2-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 131072, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/models/fireworks/kimi-k2-instruct" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/kimi-k2-instruct" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-kimi-k2-instruct-0905", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "kimi-k2-instruct-0905", "displayName": "kimi-k2-instruct-0905", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 262144, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905", "syncedAt": "2026-05-28", "sourceUrl": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/kimi-k2-instruct-0905" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/kimi-k2-thinking", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-kimi-k2-thinking", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "kimi-k2-thinking", "displayName": "kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/kimi-k2-thinking" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/kimi-k2p5", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-kimi-k2p5", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "kimi-k2p5", "displayName": "kimi-k2p5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/kimi-k2p5", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/kimi-k2p5" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p1-405b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p1-405b-instruct", "displayName": "llama-v3p1-405b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p1-405b-instruct" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p1-8b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p1-8b-instruct", "displayName": "llama-v3p1-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-7, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p1-8b-instruct" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p2-11b-vision-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p2-11b-vision-instruct", "displayName": "llama-v3p2-11b-vision-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p2-11b-vision-instruct" ], "manual_model_modalities_note": "Fireworks exact route id from official model page" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p2-1b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p2-1b-instruct", "displayName": "llama-v3p2-1b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-7, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p2-1b-instruct" ], "manual_model_modalities_note": "Official Fireworks model page says the model is text in/text out and marks image input as not supported." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p2-3b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p2-3b-instruct", "displayName": "llama-v3p2-3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-7, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p2-3b-instruct" ], "manual_model_modalities_note": "Official Fireworks model page says the model is text in/text out and marks image input as not supported." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p2-90b-vision-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p2-90b-vision-instruct", "displayName": "llama-v3p2-90b-vision-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "response_schema": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-7, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false, "supports_vision": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p2-90b-vision-instruct" ], "manual_model_modalities_note": "Official Fireworks model page says the model supports both image and text input." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama4-maverick-instruct-basic", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama4-maverick-instruct-basic", "displayName": "llama4-maverick-instruct-basic", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 2.2e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-7, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama4-maverick-instruct-basic" ], "manual_model_modalities_note": "Official Fireworks model page says the Llama 4 collection is natively multimodal with text and image understanding." }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama4-scout-instruct-basic", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama4-scout-instruct-basic", "displayName": "llama4-scout-instruct-basic", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama4-scout-instruct-basic" ], "manual_model_modalities_note": "Official Fireworks model page says it is optimized for both text and image inputs." }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/minimax-m2p1", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-minimax-m2p1", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "minimax-m2p1", "displayName": "minimax-m2p1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 204800, "maxInputTokens": 204800, "maxOutputTokens": 204800, "maxTokens": 204800, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/minimax-m2p1", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/models/fireworks/minimax-m2p1" }, "rawLitellm": { "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 3e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 204800, "max_output_tokens": 204800, "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/minimax-m2p1", "https://fireworks.ai/models?modelTypes=LLM" ], "manual_model_modalities_note": "Text-only LLM; Fireworks model page lists image input as not supported." }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mixtral-8x22b-instruct-hf", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mixtral-8x22b-instruct-hf", "displayName": "mixtral-8x22b-instruct-hf", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.fireworks.ai/fine-tuning/fine-tuning-legacy", "https://fireworks.ai/models/fireworks/mixtral-8x22b-instruct", "https://fireworks.ai/models?modelTypes=LLM" ], "manual_model_modalities_note": "Exact HF alias is documented in Fireworks fine-tuning docs; the corresponding model page lists image input as not supported." }, "benchmarks": { "gsm8kmaj8_8shot_mixtral8x22binstruct_officiallaunchpost_212": { "label": "GSM8K maj@8", "category": "math", "score": 90.8, "scoreText": "90.8%", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on GSM8K maj@8." }, "mathmaj4_4shot_mixtral8x22binstruct_officiallaunchpost_213": { "label": "Math maj@4", "category": "math", "score": 44.6, "scoreText": "44.6%", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on Math maj@4." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2-72b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2-72b-instruct", "displayName": "qwen2-72b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 9e-7, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2-72b-instruct" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "mmlu_score_qwen272b_officialmodelcard_154": { "label": "MMLU", "category": "general_knowledge", "score": 84.2, "scoreText": "84.2", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-72B", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-72B", "exactModelOrSnapshot": "Qwen2-72B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "mmlupro_score_qwen272b_officialmodelcard_155": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 55.6, "scoreText": "55.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-72B", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-72B", "exactModelOrSnapshot": "Qwen2-72B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqa_score_qwen272b_officialmodelcard_156": { "label": "GPQA", "category": "reasoning", "score": 37.9, "scoreText": "37.9", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-72B", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-72B", "exactModelOrSnapshot": "Qwen2-72B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-32b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-32b-instruct", "displayName": "qwen2p5-coder-32b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-7, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-32b-instruct" ], "manual_model_modalities_note": "Official model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/yi-large", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-yi-large", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "yi-large", "displayName": "yi-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/yi-large", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/yi-01-ai/yi-large" ], "manual_model_modalities_note": "Official model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/glm-4p7", "slug": "fireworks_ai-fireworks_ai-glm-4p7", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "glm-4p7", "displayName": "glm-4p7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 202800, "maxInputTokens": 202800, "maxOutputTokens": 202800, "maxTokens": 202800, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.fireworks.ai/updates/changelog" ], "checkedAt": "2026-06-02", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Fireworks changelog says serverless GLM 4.7 was removed on May 14, 2026; mapped to the exact Fireworks model slug by naming convention." }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/glm-4p7", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/models/fireworks/glm-4p7" }, "rawLitellm": { "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 0.0000022, "source": "https://fireworks.ai/models/fireworks/glm-4p7", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/glm-4p7", "https://huggingface.co/zai-org/GLM-4.7" ], "manual_model_modalities_note": "Fireworks marks image input unsupported; the official Hugging Face card classifies the model as text-generation.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.fireworks.ai/updates/changelog" ], "manual_model_lifecycle_checked_at": "2026-06-02", "manual_model_lifecycle_note": "Fireworks changelog says serverless GLM 4.7 was removed on May 14, 2026; mapped to the exact Fireworks model slug by naming convention." }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "fireworks_ai/fireworks_ai/glm-5p1", "slug": "fireworks_ai-fireworks_ai-glm-5p1", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "glm-5p1", "displayName": "glm-5p1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.4, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.26, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.6e-7, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 202800, "maxInputTokens": 202800, "maxOutputTokens": 202800, "maxTokens": 202800, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "reasoning": true, "response_schema": false, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/glm-5p1", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/models/fireworks/glm-5p1" }, "rawLitellm": { "cache_read_input_token_cost": 2.6e-7, "input_cost_per_token": 0.0000014, "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 0.0000044, "source": "https://fireworks.ai/models/fireworks/glm-5p1", "supports_function_calling": false, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/glm-5p1", "https://huggingface.co/zai-org/GLM-5.1" ], "manual_model_modalities_note": "Fireworks marks image input unsupported; the official Hugging Face card classifies the model as text-generation." }, "benchmarks": { "hle_score_glm5_officialmodelcard_165": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 30.5, "scoreText": "30.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "gpqadiamond_score_glm5_officialmodelcard_166": { "label": "GPQA Diamond", "category": "reasoning", "score": 86, "scoreText": "86.0", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchverified_score_glm5_officialmodelcard_167": { "label": "SWE-bench Verified", "category": "coding", "score": 77.8, "scoreText": "77.8", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "fireworks_ai/fireworks_ai/kimi-k2p5", "slug": "fireworks_ai-fireworks_ai-kimi-k2p5", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "kimi-k2p5", "displayName": "kimi-k2p5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/kimi-k2p5", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/kimi-k2p5", "https://huggingface.co/moonshotai/Kimi-K2.5" ], "manual_model_modalities_note": "The Fireworks page says Kimi K2.5 unifies vision and text; the official Hugging Face card uses image-text-to-text." } }, { "id": "fireworks_ai/fireworks_ai/minimax-m2p1", "slug": "fireworks_ai-fireworks_ai-minimax-m2p1", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "minimax-m2p1", "displayName": "minimax-m2p1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 204800, "maxInputTokens": 204800, "maxOutputTokens": 204800, "maxTokens": 204800, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/minimax-m2p1", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/models/fireworks/minimax-m2p1" }, "rawLitellm": { "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 3e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 204800, "max_output_tokens": 204800, "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/minimax-m2p1", "https://huggingface.co/MiniMaxAI/MiniMax-M2.1" ], "manual_model_modalities_note": "Fireworks marks image input unsupported; the official Hugging Face card classifies the model as text-generation." }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "fireworks_ai-embedding-models/fireworks_ai/nomic-ai/nomic-embed-text-v1", "slug": "fireworks_ai-embedding-models-fireworks_ai-nomic-ai-nomic-embed-text-v1", "provider": "fireworks_ai-embedding-models", "providerSlug": "fireworks_ai-embedding-models", "name": "nomic-embed-text-v1", "displayName": "nomic-embed-text-v1", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.008, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.008, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-9, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/nomic-ai/nomic-embed-text-v1", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 8e-9, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "source": "https://fireworks.ai/pricing" }, "benchmarks": { "local_performancebenchmarks_mteb_nomicembedtextv1_officialmodelcard_319": { "label": "Performance Benchmarks", "category": "other", "score": 62.39, "scoreText": "62.39", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported model-card benchmark table." }, "local_performancebenchmarks_loco_nomicembedtextv1_officialmodelcard_320": { "label": "Performance Benchmarks", "category": "long_context", "score": 85.53, "scoreText": "85.53", "metric": "LoCo", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported model-card benchmark table." }, "local_performancebenchmarks_jinalongcontext_nomicembedtextv1_officialmodelcard_321": { "label": "Performance Benchmarks", "category": "long_context", "score": 54.16, "scoreText": "54.16", "metric": "Jina Long Context", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported model-card benchmark table." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_322": { "label": "Adjusting Dimensionality", "category": "other", "score": 62.28, "scoreText": "62.28", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 768 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_323": { "label": "Adjusting Dimensionality", "category": "other", "score": 61.96, "scoreText": "61.96", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 512 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_324": { "label": "Adjusting Dimensionality", "category": "other", "score": 61.04, "scoreText": "61.04", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 256 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_325": { "label": "Adjusting Dimensionality", "category": "other", "score": 59.34, "scoreText": "59.34", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 128 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_326": { "label": "Adjusting Dimensionality", "category": "other", "score": 56.1, "scoreText": "56.10", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 64 row from the model card." } } }, { "id": "fireworks_ai-embedding-models/fireworks_ai/nomic-ai/nomic-embed-text-v1.5", "slug": "fireworks_ai-embedding-models-fireworks_ai-nomic-ai-nomic-embed-text-v1-5", "provider": "fireworks_ai-embedding-models", "providerSlug": "fireworks_ai-embedding-models", "name": "nomic-embed-text-v1.5", "displayName": "nomic-embed-text-v1.5", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.008, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.008, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-9, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/nomic-ai/nomic-embed-text-v1.5", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 8e-9, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "source": "https://fireworks.ai/pricing" }, "benchmarks": { "local_performancebenchmarks_mteb_nomicembedtextv1_officialmodelcard_319": { "label": "Performance Benchmarks", "category": "other", "score": 62.39, "scoreText": "62.39", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported model-card benchmark table." }, "local_performancebenchmarks_loco_nomicembedtextv1_officialmodelcard_320": { "label": "Performance Benchmarks", "category": "long_context", "score": 85.53, "scoreText": "85.53", "metric": "LoCo", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported model-card benchmark table." }, "local_performancebenchmarks_jinalongcontext_nomicembedtextv1_officialmodelcard_321": { "label": "Performance Benchmarks", "category": "long_context", "score": 54.16, "scoreText": "54.16", "metric": "Jina Long Context", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported model-card benchmark table." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_322": { "label": "Adjusting Dimensionality", "category": "other", "score": 62.28, "scoreText": "62.28", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 768 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_323": { "label": "Adjusting Dimensionality", "category": "other", "score": 61.96, "scoreText": "61.96", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 512 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_324": { "label": "Adjusting Dimensionality", "category": "other", "score": 61.04, "scoreText": "61.04", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 256 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_325": { "label": "Adjusting Dimensionality", "category": "other", "score": 59.34, "scoreText": "59.34", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 128 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_326": { "label": "Adjusting Dimensionality", "category": "other", "score": 56.1, "scoreText": "56.10", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 64 row from the model card." } } }, { "id": "fireworks_ai-embedding-models/fireworks_ai/thenlper/gte-base", "slug": "fireworks_ai-embedding-models-fireworks_ai-thenlper-gte-base", "provider": "fireworks_ai-embedding-models", "providerSlug": "fireworks_ai-embedding-models", "name": "gte-base", "displayName": "gte-base", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.008, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.008, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-9, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/thenlper/gte-base", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 8e-9, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "source": "https://fireworks.ai/pricing" }, "benchmarks": { "local_mgteretrievaltable_avg_gtemultilingualbasedense_paper_344": { "label": "mGTE retrieval table", "category": "long_context", "score": 66.7, "scoreText": "66.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Dense", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_gtemultilingualbasesparse_paper_345": { "label": "mGTE retrieval table", "category": "long_context", "score": 57.2, "scoreText": "57.2", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Sparse", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_gtemultilingualbasedensesparse_paper_346": { "label": "mGTE retrieval table", "category": "long_context", "score": 68.9, "scoreText": "68.9", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Dense + Sparse", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "fireworks_ai-embedding-models/fireworks_ai/thenlper/gte-large", "slug": "fireworks_ai-embedding-models-fireworks_ai-thenlper-gte-large", "provider": "fireworks_ai-embedding-models", "providerSlug": "fireworks_ai-embedding-models", "name": "gte-large", "displayName": "gte-large", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.016, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.016, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.6e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/thenlper/gte-large", "syncedAt": "2026-05-28", "sourceUrl": "https://fireworks.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1.6e-8, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "source": "https://fireworks.ai/pricing" }, "benchmarks": { "local_mgteretrievaltable_avg_gtemultilingualbasedense_paper_344": { "label": "mGTE retrieval table", "category": "long_context", "score": 66.7, "scoreText": "66.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Dense", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_gtemultilingualbasesparse_paper_345": { "label": "mGTE retrieval table", "category": "long_context", "score": 57.2, "scoreText": "57.2", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Sparse", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_gtemultilingualbasedensesparse_paper_346": { "label": "mGTE retrieval table", "category": "long_context", "score": 68.9, "scoreText": "68.9", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "gte", "exactModelOrSnapshot": "gte-multilingual-base Dense + Sparse", "modelDeveloper": "Alibaba-NLP", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "friendliai/friendliai/meta-llama-3.1-70b-instruct", "slug": "friendliai-friendliai-meta-llama-3-1-70b-instruct", "provider": "friendliai", "providerSlug": "friendliai", "name": "meta-llama-3.1-70b-instruct", "displayName": "meta-llama-3.1-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "friendliai/meta-llama-3.1-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "friendliai", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "friendliai/friendliai/meta-llama-3.1-8b-instruct", "slug": "friendliai-friendliai-meta-llama-3-1-8b-instruct", "provider": "friendliai", "providerSlug": "friendliai", "name": "meta-llama-3.1-8b-instruct", "displayName": "meta-llama-3.1-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "friendliai/meta-llama-3.1-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "friendliai", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "text-completion-openai/ft:babbage-002", "slug": "text-completion-openai-ft-babbage-002", "provider": "text-completion-openai", "providerSlug": "text-completion-openai", "name": "ft:babbage-002", "displayName": "ft:babbage-002", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 1.5999999999999999, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.19999999999999998, "batchOutputUsdPer1MTokens": 0.19999999999999998, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000016, "input_cost_per_token_batches": 2e-7, "output_cost_per_token": 0.0000016, "output_cost_per_token_batches": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:babbage-002", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000016, "input_cost_per_token_batches": 2e-7, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0000016, "output_cost_per_token_batches": 2e-7 } }, { "id": "text-completion-openai/ft:davinci-002", "slug": "text-completion-openai-ft-davinci-002", "provider": "text-completion-openai", "providerSlug": "text-completion-openai", "name": "ft:davinci-002", "displayName": "ft:davinci-002", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 12, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 1, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000012, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:davinci-002", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000012, "input_cost_per_token_batches": 0.000001, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000001 } }, { "id": "openai/ft:gpt-3.5-turbo", "slug": "openai-ft-gpt-3-5-turbo", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-3.5-turbo", "displayName": "ft:gpt-3.5-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.5, "batchOutputUsdPer1MTokens": 3, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "input_cost_per_token_batches": 0.0000015, "output_cost_per_token": 0.000006, "output_cost_per_token_batches": 0.000003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-3.5-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "input_cost_per_token_batches": 0.0000015, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000006, "output_cost_per_token_batches": 0.000003, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/ft:gpt-3.5-turbo-0125", "slug": "openai-ft-gpt-3-5-turbo-0125", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-3.5-turbo-0125", "displayName": "ft:gpt-3.5-turbo-0125", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-3.5-turbo-0125", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000006, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/ft:gpt-3.5-turbo-0613", "slug": "openai-ft-gpt-3-5-turbo-0613", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-3.5-turbo-0613", "displayName": "ft:gpt-3.5-turbo-0613", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-3.5-turbo-0613", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "openai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000006, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/ft:gpt-3.5-turbo-1106", "slug": "openai-ft-gpt-3-5-turbo-1106", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-3.5-turbo-1106", "displayName": "ft:gpt-3.5-turbo-1106", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-3.5-turbo-1106", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000006, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/ft:gpt-4-0613", "slug": "openai-ft-gpt-4-0613", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-4-0613", "displayName": "ft:gpt-4-0613", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-4-0613", "syncedAt": "2026-05-28", "sourceUrl": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing" }, "rawLitellm": { "input_cost_per_token": 0.00003, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00006, "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/ft:gpt-4o-2024-08-06", "slug": "openai-ft-gpt-4o-2024-08-06", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-4o-2024-08-06", "displayName": "ft:gpt-4o-2024-08-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.75, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 1.875, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.875, "batchOutputUsdPer1MTokens": 7.5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000001875, "input_cost_per_token": 0.00000375, "input_cost_per_token_batches": 0.000001875, "output_cost_per_token": 0.000015, "output_cost_per_token_batches": 0.0000075 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-4o-2024-08-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.000001875, "input_cost_per_token": 0.00000375, "input_cost_per_token_batches": 0.000001875, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_batches": 0.0000075, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/ft:gpt-4o-2024-11-20", "slug": "openai-ft-gpt-4o-2024-11-20", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-4o-2024-11-20", "displayName": "ft:gpt-4o-2024-11-20", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.75, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": 1.875, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000001875, "input_cost_per_token": 0.00000375, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-4o-2024-11-20", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000001875, "input_cost_per_token": 0.00000375, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/ft:gpt-4o-mini-2024-07-18", "slug": "openai-ft-gpt-4o-mini-2024-07-18", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-4o-mini-2024-07-18", "displayName": "ft:gpt-4o-mini-2024-07-18", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.15, "batchOutputUsdPer1MTokens": 0.6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 3e-7, "input_cost_per_token_batches": 1.5e-7, "output_cost_per_token": 0.0000012, "output_cost_per_token_batches": 6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-4o-mini-2024-07-18", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 3e-7, "input_cost_per_token_batches": 1.5e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000012, "output_cost_per_token_batches": 6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/ft:gpt-4.1-2025-04-14", "slug": "openai-ft-gpt-4-1-2025-04-14", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-4.1-2025-04-14", "displayName": "ft:gpt-4.1-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.75, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.5, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_batches": 0.0000015, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-4.1-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_batches": 0.0000015, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "openai/ft:gpt-4.1-mini-2025-04-14", "slug": "openai-ft-gpt-4-1-mini-2025-04-14", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-4.1-mini-2025-04-14", "displayName": "ft:gpt-4.1-mini-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 3.1999999999999997, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.39999999999999997, "batchOutputUsdPer1MTokens": 1.5999999999999999, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 8e-7, "input_cost_per_token_batches": 4e-7, "output_cost_per_token": 0.0000032, "output_cost_per_token_batches": 0.0000016 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-4.1-mini-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 8e-7, "input_cost_per_token_batches": 4e-7, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000032, "output_cost_per_token_batches": 0.0000016, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt41mini_officiallaunchpost_5": { "label": "SWE-bench Verified", "category": "coding", "score": 23.6, "scoreText": "23.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-mini", "exactModelOrSnapshot": "GPT-4.1 mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table for the GPT-4.1 family." } } }, { "id": "openai/ft:gpt-4.1-nano-2025-04-14", "slug": "openai-ft-gpt-4-1-nano-2025-04-14", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:gpt-4.1-nano-2025-04-14", "displayName": "ft:gpt-4.1-nano-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.09999999999999999, "batchOutputUsdPer1MTokens": 0.39999999999999997, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_batches": 1e-7, "output_cost_per_token": 8e-7, "output_cost_per_token_batches": 4e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:gpt-4.1-nano-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_batches": 1e-7, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-7, "output_cost_per_token_batches": 4e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "aime24_accuracy_gpt41nano_officiallaunchpost_6": { "label": "AIME 2024", "category": "reasoning", "score": 29.4, "scoreText": "29.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-nano", "exactModelOrSnapshot": "GPT-4.1 nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Academic-knowledge appendix comparison row for the nano model." }, "mmlu_accuracy_gpt41nano_officiallaunchpost_258": { "label": "MMLU", "category": "general_knowledge", "score": 80.1, "scoreText": "80.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the narrative and table." }, "gpqa_accuracy_gpt41nano_officiallaunchpost_259": { "label": "GPQA", "category": "reasoning", "score": 50.3, "scoreText": "50.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." }, "aiderpolyglotcoding_passrate_gpt41nano_officiallaunchpost_260": { "label": "Aider Polyglot", "category": "coding", "score": 9.8, "scoreText": "9.8%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." } } }, { "id": "openai/ft:o4-mini-2025-04-16", "slug": "openai-ft-o4-mini-2025-04-16", "provider": "OpenAI", "providerSlug": "openai", "name": "ft:o4-mini-2025-04-16", "displayName": "ft:o4-mini-2025-04-16", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 4, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": 1, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 2, "batchOutputUsdPer1MTokens": 8, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000001, "input_cost_per_token": 0.000004, "input_cost_per_token_batches": 0.000002, "output_cost_per_token": 0.000016, "output_cost_per_token_batches": 0.000008 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ft:o4-mini-2025-04-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.000001, "input_cost_per_token": 0.000004, "input_cost_per_token_batches": 0.000002, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000016, "output_cost_per_token_batches": 0.000008, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "aime2025_accuracy_openaio4minihigh_officiallaunchpost_15": { "label": "AIME 2025", "category": "reasoning", "score": 92.7, "scoreText": "92.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio4minihigh_officiallaunchpost_16": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 81.4, "scoreText": "81.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio4minihigh_officiallaunchpost_17": { "label": "SWE-bench Verified", "category": "coding", "score": 68.1, "scoreText": "68.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "vertex_ai-language-models/gemini-2.0-flash", "slug": "vertex_ai-language-models-gemini-2-0-flash", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.0-flash", "displayName": "gemini-2.0-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.7, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01" }, "source": { "type": "litellm", "litellmKey": "gemini-2.0-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing#2_0flash" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 4e-7, "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash" ], "manual_model_modalities_note": "Google Gemini exact-model override from model page" }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." } } }, { "id": "vertex_ai-language-models/gemini-2.0-flash-001", "slug": "vertex_ai-language-models-gemini-2-0-flash-001", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.0-flash-001", "displayName": "gemini-2.0-flash-001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": 0.0375, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3.75e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": true, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": true, "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01" }, "source": { "type": "litellm", "litellmKey": "gemini-2.0-flash-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 3.75e-8, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 1.5e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash" ], "manual_model_modalities_note": "Google Gemini exact alias override from version list" }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." } } }, { "id": "vertex_ai-language-models/gemini-2.0-flash-lite", "slug": "vertex_ai-language-models-gemini-2-0-flash-lite", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.0-flash-lite", "displayName": "gemini-2.0-flash-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": 0.01875, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.075, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.875e-8, "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": null, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 50, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": true, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": true, "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01" }, "source": { "type": "litellm", "litellmKey": "gemini-2.0-flash-lite", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash" }, "rawLitellm": { "cache_read_input_token_cost": 1.875e-8, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 50, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash-lite", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Audio, images, video, and text Output Text" }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "mmlupro_accuracy_gemini20flashlitepublicpreview_officialmodelcard_79": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashlitepublicpreview_officialmodelcard_80": { "label": "LiveCodeBench v5", "category": "coding", "score": 28.9, "scoreText": "28.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashlitepublicpreview_officialmodelcard_81": { "label": "GPQA Diamond", "category": "science", "score": 51.5, "scoreText": "51.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "math_accuracy_gemini20flashlitepublicpreview_officialmodelcard_82": { "label": "MATH", "category": "math", "score": 86.8, "scoreText": "86.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashlitepublicpreview_officialmodelcard_83": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." } } }, { "id": "vertex_ai-language-models/gemini-2.0-flash-lite-001", "slug": "vertex_ai-language-models-gemini-2-0-flash-lite-001", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.0-flash-lite-001", "displayName": "gemini-2.0-flash-lite-001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": 0.01875, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.075, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.875e-8, "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": null, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 50, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": true, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": true, "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01" }, "source": { "type": "litellm", "litellmKey": "gemini-2.0-flash-lite-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash" }, "rawLitellm": { "cache_read_input_token_cost": 1.875e-8, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 50, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash-lite" ], "manual_model_modalities_note": "Google Gemini exact alias override from version list" }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "mmlupro_accuracy_gemini20flashlitepublicpreview_officialmodelcard_79": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashlitepublicpreview_officialmodelcard_80": { "label": "LiveCodeBench v5", "category": "coding", "score": 28.9, "scoreText": "28.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashlitepublicpreview_officialmodelcard_81": { "label": "GPQA Diamond", "category": "science", "score": 51.5, "scoreText": "51.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "math_accuracy_gemini20flashlitepublicpreview_officialmodelcard_82": { "label": "MATH", "category": "math", "score": 86.8, "scoreText": "86.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashlitepublicpreview_officialmodelcard_83": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." } } }, { "id": "vertex_ai-language-models/gemini-2.5-flash", "slug": "vertex_ai-language-models-gemini-2-5-flash", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.5-flash", "displayName": "gemini-2.5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview" }, "rawLitellm": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, images, video, audio Output Text" } }, { "id": "vertex_ai-language-models/gemini-2.5-flash-image", "slug": "vertex_ai-language-models-gemini-2-5-flash-image", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.5-flash-image", "displayName": "gemini-2.5-flash-image", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 39000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_image": 0.039, "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "tpm": 8000000 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 100000, "tpm": 8000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": false, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "image", "text" ], "output": [ "image", "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-flash-image", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image" }, "rawLitellm": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "max_pdf_size_mb": 30, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": false, "tpm": 8000000, "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Images and text Output Images and text" } }, { "id": "vertex_ai-language-models/gemini-3-pro-image-preview", "slug": "vertex_ai-language-models-gemini-3-pro-image-preview", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3-pro-image-preview", "displayName": "gemini-3-pro-image-preview", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 1100, "imageOutputUsdPer1MUnits": 134000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 32768, "maxInputTokens": 65536, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "prompt_caching": true, "response_schema": true, "system_messages": true, "vision": true, "web_search": true, "service_tier": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "image", "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-3-pro-image-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Image and Text Output Image and Text" }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "vertex_ai-language-models/gemini-3.1-flash-image-preview", "slug": "vertex_ai-language-models-gemini-3-1-flash-image-preview", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3.1-flash-image-preview", "displayName": "gemini-3.1-flash-image-preview", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 560, "imageOutputUsdPer1MUnits": 67200, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-7, "output_cost_per_image": 0.0672, "output_cost_per_image_token": 0.00006, "output_cost_per_token": 0.000003, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 32768, "maxInputTokens": 65536, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "prompt_caching": true, "response_schema": true, "system_messages": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "pdf", "text" ], "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-3.1-flash-image-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "rawLitellm": { "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-7, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 0.00006, "output_cost_per_token": 0.000003, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text and Image / PDF Output Image and Text" } }, { "id": "vertex_ai-language-models/gemini-3.1-flash-lite-preview", "slug": "vertex_ai-language-models-gemini-3-1-flash-lite-preview", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3.1-flash-lite-preview", "displayName": "gemini-3.1-flash-lite-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 1.5, "audioInputUsdPer1MTokens": 0.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": false, "code_execution": true, "file_search": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-3.1-flash-lite-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "source": "https://ai.google.dev/gemini-api/docs/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_code_execution": true, "supports_file_search": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text" } }, { "id": "vertex_ai-language-models/gemini-3.1-flash-lite", "slug": "vertex_ai-language-models-gemini-3-1-flash-lite", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3.1-flash-lite", "displayName": "gemini-3.1-flash-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 1.5, "audioInputUsdPer1MTokens": 0.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.125, "batchOutputUsdPer1MTokens": 0.75, "batchCachedInputUsdPer1MTokens": 0.012499999999999999, "priorityInputUsdPer1MTokens": 0.44999999999999996, "priorityOutputUsdPer1MTokens": 2.7, "priorityCachedInputUsdPer1MTokens": 0.045, "flexInputUsdPer1MTokens": 0.125, "flexOutputUsdPer1MTokens": 0.75, "flexCachedInputUsdPer1MTokens": 0.012499999999999999, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": false, "code_execution": true, "file_search": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-3.1-flash-lite", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_code_execution": true, "supports_file_search": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text" } }, { "id": "vertex_ai-language-models/deep-research-pro-preview-12-2025", "slug": "vertex_ai-language-models-deep-research-pro-preview-12-2025", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "deep-research-pro-preview-12-2025", "displayName": "deep-research-pro-preview-12-2025", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 1100, "imageOutputUsdPer1MUnits": 134000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 65536, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "prompt_caching": true, "response_schema": true, "system_messages": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "deep-research-pro-preview-12-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025?hl=en" ], "manual_model_modalities_note": "Google Deep Research exact-model override from model page" } }, { "id": "vertex_ai-language-models/gemini-2.5-flash-lite", "slug": "vertex_ai-language-models-gemini-2-5-flash-lite", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.5-flash-lite", "displayName": "gemini-2.5-flash-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.01, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.39999999999999997, "audioInputUsdPer1MTokens": 0.3, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-flash-lite", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview" }, "rawLitellm": { "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-lite", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, image, video, audio, PDF Output Text" }, "benchmarks": { "humanityslastexam_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_90": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 7.3, "scoreText": "7.3% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "gpqadiamond_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_91": { "label": "GPQA Diamond", "category": "science", "score": 71.7, "scoreText": "71.7% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "aime2025_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_92": { "label": "AIME 2025", "category": "math", "score": 48.2, "scoreText": "48.2% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "livecodebenchv5_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_93": { "label": "LiveCodeBench v5", "category": "coding", "score": 58.4, "scoreText": "58.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "swebenchverified_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_94": { "label": "SWE-bench Verified", "category": "agentic", "score": 38.9, "scoreText": "38.9% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "mmmu_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_95": { "label": "MMMU", "category": "multimodal", "score": 72, "scoreText": "72.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." } } }, { "id": "vertex_ai-language-models/gemini-2.5-flash-lite-preview-09-2025", "slug": "vertex_ai-language-models-gemini-2-5-flash-lite-preview-09-2025", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.5-flash-lite-preview-09-2025", "displayName": "gemini-2.5-flash-lite-preview-09-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.01, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.39999999999999997, "audioInputUsdPer1MTokens": 0.3, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-flash-lite-preview-09-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/" }, "rawLitellm": { "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-lite-preview-09-2025", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, image, video, audio, PDF Output Text" }, "benchmarks": { "humanityslastexam_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_90": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 7.3, "scoreText": "7.3% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "gpqadiamond_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_91": { "label": "GPQA Diamond", "category": "science", "score": 71.7, "scoreText": "71.7% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "aime2025_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_92": { "label": "AIME 2025", "category": "math", "score": 48.2, "scoreText": "48.2% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "livecodebenchv5_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_93": { "label": "LiveCodeBench v5", "category": "coding", "score": 58.4, "scoreText": "58.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "swebenchverified_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_94": { "label": "SWE-bench Verified", "category": "agentic", "score": 38.9, "scoreText": "38.9% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "mmmu_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_95": { "label": "MMMU", "category": "multimodal", "score": 72, "scoreText": "72.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." } } }, { "id": "vertex_ai-language-models/gemini-2.5-flash-preview-09-2025", "slug": "vertex_ai-language-models-gemini-2-5-flash-preview-09-2025", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.5-flash-preview-09-2025", "displayName": "gemini-2.5-flash-preview-09-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-flash-preview-09-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-preview-09-2025", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, images, video, audio Output Text" } }, { "id": "vertex_ai-language-models/gemini-live-2.5-flash-preview-native-audio-09-2025", "slug": "vertex_ai-language-models-gemini-live-2-5-flash-preview-native-audio-09-2025", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-live-2.5-flash-preview-native-audio-09-2025", "displayName": "gemini-live-2.5-flash-preview-native-audio-09-2025", "mode": "realtime", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 3, "audioOutputUsdPer1MTokens": 12, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_audio_token": 0.000003, "input_cost_per_token": 3e-7, "output_cost_per_audio_token": 0.000012, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/vertex_ai/live" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-live-2.5-flash-preview-native-audio-09-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_audio_token": 0.000003, "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "realtime", "output_cost_per_audio_token": 0.000012, "output_cost_per_token": 0.000002, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/vertex_ai/live" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } } }, { "id": "gemini/gemini/gemini-live-2.5-flash-preview-native-audio-09-2025", "slug": "gemini-gemini-gemini-live-2-5-flash-preview-native-audio-09-2025", "provider": "Google", "providerSlug": "gemini", "name": "gemini-live-2.5-flash-preview-native-audio-09-2025", "displayName": "gemini-live-2.5-flash-preview-native-audio-09-2025", "mode": "realtime", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 3, "audioOutputUsdPer1MTokens": 12, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_audio_token": 0.000003, "input_cost_per_token": 3e-7, "output_cost_per_audio_token": 0.000012, "output_cost_per_token": 0.000002, "rpm": 100000, "tpm": 8000000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 100000, "tpm": 8000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_audio_token": 0.000003, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "realtime", "output_cost_per_audio_token": 0.000012, "output_cost_per_token": 0.000002, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } } }, { "id": "vertex_ai-language-models/gemini-2.5-flash-lite-preview-06-17", "slug": "vertex_ai-language-models-gemini-2-5-flash-lite-preview-06-17", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.5-flash-lite-preview-06-17", "displayName": "gemini-2.5-flash-lite-preview-06-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.39999999999999997, "audioInputUsdPer1MTokens": 0.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 1e-7, "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": "2025-11-18" }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-flash-lite-preview-06-17", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview" }, "rawLitellm": { "deprecation_date": "2025-11-18", "cache_read_input_token_cost": 2.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } }, "benchmarks": { "humanityslastexam_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_90": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 7.3, "scoreText": "7.3% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "gpqadiamond_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_91": { "label": "GPQA Diamond", "category": "science", "score": 71.7, "scoreText": "71.7% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "aime2025_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_92": { "label": "AIME 2025", "category": "math", "score": 48.2, "scoreText": "48.2% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "livecodebenchv5_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_93": { "label": "LiveCodeBench v5", "category": "coding", "score": 58.4, "scoreText": "58.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "swebenchverified_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_94": { "label": "SWE-bench Verified", "category": "agentic", "score": 38.9, "scoreText": "38.9% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "mmmu_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_95": { "label": "MMMU", "category": "multimodal", "score": 72, "scoreText": "72.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." } } }, { "id": "vertex_ai-language-models/gemini-2.5-pro", "slug": "vertex_ai-language-models-gemini-2-5-pro", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.5-pro", "displayName": "gemini-2.5-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 2.5, "above200kOutputUsdPer1MTokens": 15, "above200kCachedInputUsdPer1MTokens": 0.25, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Audio, images, video, text, and PDF Output Text" }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "vertex_ai-language-models/gemini-3-pro-preview", "slug": "vertex_ai-language-models-gemini-3-pro-preview", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3-pro-preview", "displayName": "gemini-3-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5999999999999996, "priorityOutputUsdPer1MTokens": 21.6, "priorityCachedInputUsdPer1MTokens": 0.36, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": "2026-03-26" }, "source": { "type": "litellm", "litellmKey": "gemini-3-pro-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "deprecation_date": "2026-03-26", "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text" }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "vertex_ai-language-models/gemini-3.1-pro-preview", "slug": "vertex_ai-language-models-gemini-3-1-pro-preview", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3.1-pro-preview", "displayName": "gemini-3.1-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 120, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5999999999999996, "priorityOutputUsdPer1MTokens": 21.6, "priorityCachedInputUsdPer1MTokens": 0.36, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "url_context": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-3.1-pro-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text" }, "benchmarks": { "livebench_livebenchscore_gemini31propreviewhigh_benchmarkleaderboard_229": { "label": "LiveBench", "category": "general_knowledge", "score": 79.93, "scoreText": "79.93", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview High*", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; source notes this row as a high-effort variant." }, "lmarenatextarenaenglish_arenaelo_gemini31propreview_benchmarkleaderboard_240": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1490, "scoreText": "1490±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "gemini-3.1-pro-preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "gpqadiamond_accuracy_gemini31propreview_benchmarkleaderboard_245": { "label": "GPQA Diamond", "category": "science", "score": 94.1, "scoreText": "94.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Top row summarized on the Artificial Analysis GPQA Diamond leaderboard." }, "mmmupro_accuracy_gemini31propreview_benchmarkleaderboard_253": { "label": "MMMU-Pro", "category": "multimodal", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard row shown without a route qualifier." } } }, { "id": "vertex_ai-language-models/gemini-3.1-pro-preview-customtools", "slug": "vertex_ai-language-models-gemini-3-1-pro-preview-customtools", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3.1-pro-preview-customtools", "displayName": "gemini-3.1-pro-preview-customtools", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 120, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "url_context": true, "native_streaming": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-3.1-pro-preview-customtools", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview" ], "manual_model_modalities_note": "Google Gemini exact alias override from version list" }, "benchmarks": { "livebench_livebenchscore_gemini31propreviewhigh_benchmarkleaderboard_229": { "label": "LiveBench", "category": "general_knowledge", "score": 79.93, "scoreText": "79.93", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview High*", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; source notes this row as a high-effort variant." }, "lmarenatextarenaenglish_arenaelo_gemini31propreview_benchmarkleaderboard_240": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1490, "scoreText": "1490±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "gemini-3.1-pro-preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "gpqadiamond_accuracy_gemini31propreview_benchmarkleaderboard_245": { "label": "GPQA Diamond", "category": "science", "score": 94.1, "scoreText": "94.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Top row summarized on the Artificial Analysis GPQA Diamond leaderboard." }, "mmmupro_accuracy_gemini31propreview_benchmarkleaderboard_253": { "label": "MMMU-Pro", "category": "multimodal", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard row shown without a route qualifier." } } }, { "id": "vertex_ai/vertex_ai/gemini-3-pro-preview", "slug": "vertex_ai-vertex_ai-gemini-3-pro-preview", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "gemini-3-pro-preview", "displayName": "gemini-3-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5999999999999996, "priorityOutputUsdPer1MTokens": 21.6, "priorityCachedInputUsdPer1MTokens": 0.36, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-3-pro-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "litellm_provider": "vertex_ai", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query" }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "vertex_ai/vertex_ai/gemini-3-flash-preview", "slug": "vertex_ai-vertex_ai-gemini-3-flash-preview", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "gemini-3-flash-preview", "displayName": "gemini-3-flash-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.8999999999999999, "priorityOutputUsdPer1MTokens": 5.4, "priorityCachedInputUsdPer1MTokens": 0.09, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 5e-7, "input_cost_per_audio_token": 0.000001, "output_cost_per_token": 0.000003, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-3-flash-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 5e-7, "input_cost_per_audio_token": 0.000001, "litellm_provider": "vertex_ai", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query" }, "benchmarks": { "swebenchverified_resolved_gemini3flashhighreasoning_benchmarkleaderboard_215": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash (high reasoning)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_gemini3flashpreviewhigh_benchmarkleaderboard_234": { "label": "LiveBench", "category": "general_knowledge", "score": 72.4, "scoreText": "72.40", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash Preview High", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific high-effort variant." } } }, { "id": "vertex_ai/vertex_ai/gemini-3.5-flash", "slug": "vertex_ai-vertex_ai-gemini-3-5-flash", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "gemini-3.5-flash", "displayName": "gemini-3.5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 9, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 9, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.7, "priorityOutputUsdPer1MTokens": 16.2, "priorityCachedInputUsdPer1MTokens": 0.27, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.0000015, "input_cost_per_audio_token": 0.000001, "output_cost_per_reasoning_token": 0.000009, "output_cost_per_token": 0.000009, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-3.5-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.0000015, "input_cost_per_audio_token": 0.000001, "litellm_provider": "vertex_ai", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.000009, "output_cost_per_token": 0.000009, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query" }, "benchmarks": { "mmmupro_accuracy_gemini35flashhigh_benchmarkleaderboard_251": { "label": "MMMU-Pro", "category": "multimodal", "score": 84, "scoreText": "84%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.5 Flash", "exactModelOrSnapshot": "Gemini 3.5 Flash (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard top row summarized on the page." }, "mmmupro_accuracy_gemini35flashmedium_benchmarkleaderboard_252": { "label": "MMMU-Pro", "category": "multimodal", "score": 84, "scoreText": "84%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.5 Flash", "exactModelOrSnapshot": "Gemini 3.5 Flash (medium)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard row for the medium variant." } } }, { "id": "vertex_ai/vertex_ai/gemini-3.1-pro-preview", "slug": "vertex_ai-vertex_ai-gemini-3-1-pro-preview", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "gemini-3.1-pro-preview", "displayName": "gemini-3.1-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 120, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5999999999999996, "priorityOutputUsdPer1MTokens": 21.6, "priorityCachedInputUsdPer1MTokens": 0.36, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "url_context": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-3.1-pro-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "litellm_provider": "vertex_ai", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query" }, "benchmarks": { "livebench_livebenchscore_gemini31propreviewhigh_benchmarkleaderboard_229": { "label": "LiveBench", "category": "general_knowledge", "score": 79.93, "scoreText": "79.93", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview High*", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; source notes this row as a high-effort variant." }, "lmarenatextarenaenglish_arenaelo_gemini31propreview_benchmarkleaderboard_240": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1490, "scoreText": "1490±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "gemini-3.1-pro-preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "gpqadiamond_accuracy_gemini31propreview_benchmarkleaderboard_245": { "label": "GPQA Diamond", "category": "science", "score": 94.1, "scoreText": "94.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Top row summarized on the Artificial Analysis GPQA Diamond leaderboard." }, "mmmupro_accuracy_gemini31propreview_benchmarkleaderboard_253": { "label": "MMMU-Pro", "category": "multimodal", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard row shown without a route qualifier." } } }, { "id": "vertex_ai/vertex_ai/gemini-3.1-pro-preview-customtools", "slug": "vertex_ai-vertex_ai-gemini-3-1-pro-preview-customtools", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "gemini-3.1-pro-preview-customtools", "displayName": "gemini-3.1-pro-preview-customtools", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 120, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5999999999999996, "priorityOutputUsdPer1MTokens": 21.6, "priorityCachedInputUsdPer1MTokens": 0.36, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "url_context": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-3.1-pro-preview-customtools", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "litellm_provider": "vertex_ai", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query" }, "benchmarks": { "livebench_livebenchscore_gemini31propreviewhigh_benchmarkleaderboard_229": { "label": "LiveBench", "category": "general_knowledge", "score": 79.93, "scoreText": "79.93", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview High*", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; source notes this row as a high-effort variant." }, "lmarenatextarenaenglish_arenaelo_gemini31propreview_benchmarkleaderboard_240": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1490, "scoreText": "1490±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "gemini-3.1-pro-preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "gpqadiamond_accuracy_gemini31propreview_benchmarkleaderboard_245": { "label": "GPQA Diamond", "category": "science", "score": 94.1, "scoreText": "94.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Top row summarized on the Artificial Analysis GPQA Diamond leaderboard." }, "mmmupro_accuracy_gemini31propreview_benchmarkleaderboard_253": { "label": "MMMU-Pro", "category": "multimodal", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard row shown without a route qualifier." } } }, { "id": "vertex_ai-language-models/gemini-2.5-pro-preview-tts", "slug": "vertex_ai-language-models-gemini-2-5-pro-preview-tts", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.5-pro-preview-tts", "displayName": "gemini-2.5-pro-preview-tts", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.7, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 2.5, "above200kOutputUsdPer1MTokens": 15, "above200kCachedInputUsdPer1MTokens": 0.25, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "text" ], "input": [ "text" ], "output": [ "audio" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-pro-preview-tts", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro-preview-tts", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text Output Audio" }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "vertex_ai-language-models/gemini-robotics-er-1.5-preview", "slug": "vertex_ai-language-models-gemini-robotics-er-1-5-preview", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-robotics-er-1.5-preview", "displayName": "gemini-robotics-er-1.5-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "zero_raw_unclassified", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0, "input_cost_per_token": 3e-7, "input_cost_per_audio_token": 0.000001, "output_cost_per_token": 0.0000025, "output_cost_per_reasoning_token": 0.0000025 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-robotics-er-1.5-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview" }, "rawLitellm": { "cache_read_input_token_cost": 0, "input_cost_per_token": 3e-7, "input_cost_per_audio_token": 0.000001, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 0.0000025, "output_cost_per_reasoning_token": 0.0000025, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-robotics-er-1.5-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, images, video, audio Output Text" } }, { "id": "gemini/gemini/gemini-robotics-er-1.5-preview", "slug": "gemini-gemini-gemini-robotics-er-1-5-preview", "provider": "Google", "providerSlug": "gemini", "name": "gemini-robotics-er-1.5-preview", "displayName": "gemini-robotics-er-1.5-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "zero_raw_unclassified", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0, "input_cost_per_token": 3e-7, "input_cost_per_audio_token": 0.000001, "output_cost_per_token": 0.0000025, "output_cost_per_reasoning_token": 0.0000025, "tpm": 250000, "rpm": 10 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 10, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-robotics-er-1.5-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview" }, "rawLitellm": { "cache_read_input_token_cost": 0, "input_cost_per_token": 3e-7, "input_cost_per_audio_token": 0.000001, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 0.0000025, "output_cost_per_reasoning_token": 0.0000025, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "rpm": 10, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-robotics-er-1.5-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, images, video, audio Output Text" } }, { "id": "vertex_ai-language-models/gemini-2.5-computer-use-preview-10-2025", "slug": "vertex_ai-language-models-gemini-2-5-computer-use-preview-10-2025", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.5-computer-use-preview-10-2025", "displayName": "gemini-2.5-computer-use-preview-10-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 2.5, "above200kOutputUsdPer1MTokens": 15, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "computer_use": true, "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-computer-use-preview-10-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use" }, "rawLitellm": { "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "vertex_ai-language-models", "max_images_per_prompt": 3000, "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-computer-use-preview-10-2025", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Image, text Output Text" } }, { "id": "vertex_ai-embedding-models/gemini-embedding-001", "slug": "vertex_ai-embedding-models-gemini-embedding-001", "provider": "vertex_ai-embedding-models", "providerSlug": "vertex_ai-embedding-models", "name": "gemini-embedding-001", "displayName": "gemini-embedding-001", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": null, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-embedding-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" } }, { "id": "vertex_ai-embedding-models/gemini-embedding-2-preview", "slug": "vertex_ai-embedding-models-gemini-embedding-2-preview", "provider": "vertex_ai-embedding-models", "providerSlug": "vertex_ai-embedding-models", "name": "gemini-embedding-2-preview", "displayName": "gemini-embedding-2-preview", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 120, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-embedding-2-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "uses_embed_content": true } }, { "id": "vertex_ai-embedding-models/gemini-embedding-2", "slug": "vertex_ai-embedding-models-gemini-embedding-2", "provider": "vertex_ai-embedding-models", "providerSlug": "vertex_ai-embedding-models", "name": "gemini-embedding-2", "displayName": "gemini-embedding-2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 120, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "multimodal": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-embedding-2", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true } }, { "id": "vertex_ai/vertex_ai/gemini-embedding-2-preview", "slug": "vertex_ai-vertex_ai-gemini-embedding-2-preview", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "gemini-embedding-2-preview", "displayName": "gemini-embedding-2-preview", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 120, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "multimodal": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-embedding-2-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true } }, { "id": "vertex_ai/vertex_ai/gemini-embedding-2", "slug": "vertex_ai-vertex_ai-gemini-embedding-2", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "gemini-embedding-2", "displayName": "gemini-embedding-2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 120, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "multimodal": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-embedding-2", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true } }, { "id": "vertex_ai-language-models/gemini-flash-experimental", "slug": "vertex_ai-language-models-gemini-flash-experimental", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-flash-experimental", "displayName": "gemini-flash-experimental", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-flash-experimental", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "input_cost_per_character": 0, "input_cost_per_token": 0, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "uses_embed_content": true } }, { "id": "gemini/gemini/gemini-embedding-001", "slug": "gemini-gemini-gemini-embedding-001", "provider": "Google", "providerSlug": "gemini", "name": "gemini-embedding-001", "displayName": "gemini-embedding-001", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0, "rpm": 10000, "tpm": 10000000 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": null, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": 10000, "tpm": 10000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "embedding", "text" ], "input": [ "text" ], "output": [ "embedding", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": "2026-07-14", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-embedding-001", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "gemini", "max_input_tokens": 2048, "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", "tpm": 10000000, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-embedding-001", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Text Output Text embeddings", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "gemini/gemini/gemini-embedding-2-preview", "slug": "gemini-gemini-gemini-embedding-2-preview", "provider": "Google", "providerSlug": "gemini", "name": "gemini-embedding-2-preview", "displayName": "gemini-embedding-2-preview", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 120, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "output_cost_per_token": 0, "rpm": 10000, "tpm": 10000000 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": 10000, "tpm": 10000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "multimodal": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-embedding-2-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_multimodal": true, "tpm": 10000000 } }, { "id": "gemini/gemini/gemini-embedding-2", "slug": "gemini-gemini-gemini-embedding-2", "provider": "Google", "providerSlug": "gemini", "name": "gemini-embedding-2", "displayName": "gemini-embedding-2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 120, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "output_cost_per_token": 0, "rpm": 10000, "tpm": 10000000 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": 10000, "tpm": 10000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "multimodal": true } }, "modalities": { "supported": [ "audio", "embedding", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "embedding", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists this as the recommended replacement for older embedding models, but does not announce a shutdown date for gemini-embedding-2." }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-embedding-2", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_token": 2e-7, "input_cost_per_video_per_second": 0.00079, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_multimodal": true, "tpm": 10000000, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-embedding-2", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Text, image, video, audio, PDF Output Text embeddings", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists this as the recommended replacement for older embedding models, but does not announce a shutdown date for gemini-embedding-2." } }, { "id": "gemini/gemini/gemini-1.5-flash", "slug": "gemini-gemini-gemini-1-5-flash", "provider": "Google", "providerSlug": "gemini", "name": "gemini-1.5-flash", "displayName": "gemini-1.5-flash", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": 0.15, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.5e-8, "input_cost_per_token_above_128k_tokens": 1.5e-7, "output_cost_per_token": 0, "rpm": 10000, "tpm": 10000000 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": 10000, "tpm": 10000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "multimodal": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": "2025-09-29" }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-1.5-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal" }, "rawLitellm": { "deprecation_date": "2025-09-29", "input_cost_per_token": 7.5e-8, "input_cost_per_token_above_128k_tokens": 1.5e-7, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal", "supports_multimodal": true, "tpm": 10000000 } }, { "id": "gemini/gemini/gemini-2.0-flash", "slug": "gemini-gemini-gemini-2-0-flash", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.0-flash", "displayName": "gemini-2.0-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.7, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "rpm": 10000, "tpm": 10000000 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 10000, "tpm": 10000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01", "status": "deprecated", "announcementDate": null, "shutdownDate": "2026-06-01", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists a fixed shutdown date in the Gemini deprecations table." }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.0-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing#2_0flash" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 4e-7, "rpm": 10000, "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 10000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash" ], "manual_model_modalities_note": "Google Gemini exact-model override from model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists a fixed shutdown date in the Gemini deprecations table." }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." } } }, { "id": "gemini/gemini/gemini-2.0-flash-001", "slug": "gemini-gemini-gemini-2-0-flash-001", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.0-flash-001", "displayName": "gemini-2.0-flash-001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.7, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "rpm": 10000, "tpm": 10000000 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 10000, "tpm": 10000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01", "status": "deprecated", "announcementDate": null, "shutdownDate": "2026-06-01", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.0-flash-001", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing#2_0flash" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 4e-7, "rpm": 10000, "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "tpm": 10000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash" ], "manual_model_modalities_note": "Google Gemini exact alias override from version list", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." } } }, { "id": "gemini/gemini/gemini-2.0-flash-lite", "slug": "gemini-gemini-gemini-2-0-flash-lite", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.0-flash-lite", "displayName": "gemini-2.0-flash-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": 0.01875, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.075, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.875e-8, "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "rpm": 4000, "tpm": 4000000 } }, "limits": { "contextWindow": null, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": null, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 50, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 4000, "tpm": 4000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": true, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": true, "function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01", "status": "deprecated", "announcementDate": null, "shutdownDate": "2026-06-01", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.0-flash-lite", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite" }, "rawLitellm": { "cache_read_input_token_cost": 1.875e-8, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 50, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 3e-7, "rpm": 4000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "tpm": 4000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash-lite", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Audio, images, video, and text Output Text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "mmlupro_accuracy_gemini20flashlitepublicpreview_officialmodelcard_79": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashlitepublicpreview_officialmodelcard_80": { "label": "LiveCodeBench v5", "category": "coding", "score": 28.9, "scoreText": "28.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashlitepublicpreview_officialmodelcard_81": { "label": "GPQA Diamond", "category": "science", "score": 51.5, "scoreText": "51.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "math_accuracy_gemini20flashlitepublicpreview_officialmodelcard_82": { "label": "MATH", "category": "math", "score": 86.8, "scoreText": "86.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashlitepublicpreview_officialmodelcard_83": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." } } }, { "id": "gemini/gemini/gemini-2.5-flash", "slug": "gemini-gemini-gemini-2-5-flash", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash", "displayName": "Gemini 2.5 Flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "tpm": 8000000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 100000, "tpm": 8000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": "2026-10-16", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview" }, "rawLitellm": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, images, video, audio Output Text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "gemini/gemini/gemini-2.5-flash-image", "slug": "gemini-gemini-gemini-2-5-flash-image", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-image", "displayName": "gemini-2.5-flash-image", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 39000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_image": 0.039, "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "tpm": 8000000 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 100000, "tpm": 8000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": false, "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "image", "text" ], "output": [ "image", "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": "2026-10-02", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-flash-image", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image" }, "rawLitellm": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "supports_reasoning": false, "max_images_per_prompt": 3000, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "max_pdf_size_mb": 30, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Images and text Output Images and text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "gemini/gemini/gemini-3-pro-image-preview", "slug": "gemini-gemini-gemini-3-pro-image-preview", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3-pro-image-preview", "displayName": "gemini-3-pro-image-preview", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 1100, "imageOutputUsdPer1MUnits": 134000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 32768, "maxInputTokens": 65536, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 1000, "tpm": 4000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "prompt_caching": true, "response_schema": true, "system_messages": true, "vision": true, "web_search": true, "service_tier": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "image", "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": null, "shutdownDate": "2026-06-25", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-3-pro-image-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Image and Text Output Image and Text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "gemini/gemini/gemini-3.1-flash-image-preview", "slug": "gemini-gemini-gemini-3-1-flash-image-preview", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3.1-flash-image-preview", "displayName": "gemini-3.1-flash-image-preview", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 45000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.125, "batchOutputUsdPer1MTokens": 0.75, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "input_cost_per_token_batches": 1.25e-7, "output_cost_per_image": 0.045, "output_cost_per_image_token": 0.00006, "output_cost_per_image_token_batches": 0.00003, "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "rpm": 1000, "tpm": 4000000, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 32768, "maxInputTokens": 65536, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 1000, "tpm": 4000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "prompt_caching": true, "response_schema": true, "system_messages": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "pdf", "text" ], "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-3.1-flash-image-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "input_cost_per_token_batches": 1.25e-7, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 0.00006, "output_cost_per_image_token_batches": 0.00003, "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "rpm": 1000, "tpm": 4000000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text and Image / PDF Output Image and Text" } }, { "id": "gemini/gemini/deep-research-pro-preview-12-2025", "slug": "gemini-gemini-deep-research-pro-preview-12-2025", "provider": "Google", "providerSlug": "gemini", "name": "deep-research-pro-preview-12-2025", "displayName": "deep-research-pro-preview-12-2025", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 1100, "imageOutputUsdPer1MUnits": 134000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 65536, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 1000, "tpm": 4000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "prompt_caching": true, "response_schema": true, "system_messages": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/deep-research-pro-preview-12-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025?hl=en" ], "manual_model_modalities_note": "Google Deep Research exact-model override from model page" } }, { "id": "gemini/gemini/gemini-2.5-flash-lite", "slug": "gemini-gemini-gemini-2-5-flash-lite", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-lite", "displayName": "gemini-2.5-flash-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.01, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.39999999999999997, "audioInputUsdPer1MTokens": 0.3, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, "tpm": 250000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 15, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": "2026-10-16", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-flash-lite", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite" }, "rawLitellm": { "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-lite", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, image, video, audio, PDF Output Text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "humanityslastexam_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_90": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 7.3, "scoreText": "7.3% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "gpqadiamond_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_91": { "label": "GPQA Diamond", "category": "science", "score": 71.7, "scoreText": "71.7% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "aime2025_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_92": { "label": "AIME 2025", "category": "math", "score": 48.2, "scoreText": "48.2% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "livecodebenchv5_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_93": { "label": "LiveCodeBench v5", "category": "coding", "score": 58.4, "scoreText": "58.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "swebenchverified_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_94": { "label": "SWE-bench Verified", "category": "agentic", "score": 38.9, "scoreText": "38.9% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "mmmu_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_95": { "label": "MMMU", "category": "multimodal", "score": 72, "scoreText": "72.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." } } }, { "id": "gemini/gemini/gemini-2.5-flash-lite-preview-09-2025", "slug": "gemini-gemini-gemini-2-5-flash-lite-preview-09-2025", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-lite-preview-09-2025", "displayName": "gemini-2.5-flash-lite-preview-09-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.01, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.39999999999999997, "audioInputUsdPer1MTokens": 0.3, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, "tpm": 250000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 15, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-flash-lite-preview-09-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/" }, "rawLitellm": { "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-lite-preview-09-2025", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, image, video, audio, PDF Output Text" }, "benchmarks": { "humanityslastexam_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_90": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 7.3, "scoreText": "7.3% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "gpqadiamond_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_91": { "label": "GPQA Diamond", "category": "science", "score": 71.7, "scoreText": "71.7% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "aime2025_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_92": { "label": "AIME 2025", "category": "math", "score": 48.2, "scoreText": "48.2% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "livecodebenchv5_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_93": { "label": "LiveCodeBench v5", "category": "coding", "score": 58.4, "scoreText": "58.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "swebenchverified_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_94": { "label": "SWE-bench Verified", "category": "agentic", "score": 38.9, "scoreText": "38.9% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "mmmu_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_95": { "label": "MMMU", "category": "multimodal", "score": 72, "scoreText": "72.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." } } }, { "id": "gemini/gemini/gemini-2.5-flash-preview-09-2025", "slug": "gemini-gemini-gemini-2-5-flash-preview-09-2025", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-preview-09-2025", "displayName": "gemini-2.5-flash-preview-09-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 15, "tpm": 250000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 15, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-flash-preview-09-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 15, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-preview-09-2025", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, images, video, audio Output Text" } }, { "id": "gemini/gemini/gemini-flash-latest", "slug": "gemini-gemini-gemini-flash-latest", "provider": "Google", "providerSlug": "gemini", "name": "gemini-flash-latest", "displayName": "gemini-flash-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 15, "tpm": 250000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 15, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-flash-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 15, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } } }, { "id": "gemini/gemini/gemini-flash-lite-latest", "slug": "gemini-gemini-gemini-flash-lite-latest", "provider": "Google", "providerSlug": "gemini", "name": "gemini-flash-lite-latest", "displayName": "gemini-flash-lite-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.39999999999999997, "audioInputUsdPer1MTokens": 0.3, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, "tpm": 250000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 15, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-flash-lite-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } } }, { "id": "gemini/gemini/gemini-2.5-flash-lite-preview-06-17", "slug": "gemini-gemini-gemini-2-5-flash-lite-preview-06-17", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-lite-preview-06-17", "displayName": "gemini-2.5-flash-lite-preview-06-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.39999999999999997, "audioInputUsdPer1MTokens": 0.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 1e-7, "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, "tpm": 250000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 15, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": "2025-11-18", "status": "retired", "announcementDate": "2025-11-04", "shutdownDate": "2025-11-18", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/changelog", "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-06-03", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google Gemini release notes list this exact preview model under the 2025-11-04 deprecation announcement for shutdown on 2025-11-18; deprecations page routes preview deprecations to release notes." }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-flash-lite-preview-06-17", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite" }, "rawLitellm": { "deprecation_date": "2025-11-18", "cache_read_input_token_cost": 2.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/changelog", "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-06-03", "manual_model_lifecycle_note": "Google Gemini release notes list this exact preview model under the 2025-11-04 deprecation announcement for shutdown on 2025-11-18; deprecations page routes preview deprecations to release notes." }, "benchmarks": { "humanityslastexam_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_90": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 7.3, "scoreText": "7.3% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "gpqadiamond_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_91": { "label": "GPQA Diamond", "category": "science", "score": 71.7, "scoreText": "71.7% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "aime2025_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_92": { "label": "AIME 2025", "category": "math", "score": 48.2, "scoreText": "48.2% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "livecodebenchv5_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_93": { "label": "LiveCodeBench v5", "category": "coding", "score": 58.4, "scoreText": "58.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "swebenchverified_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_94": { "label": "SWE-bench Verified", "category": "agentic", "score": 38.9, "scoreText": "38.9% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "mmmu_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_95": { "label": "MMMU", "category": "multimodal", "score": 72, "scoreText": "72.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." } } }, { "id": "gemini/gemini/gemini-2.5-flash-preview-tts", "slug": "gemini-gemini-gemini-2-5-flash-preview-tts", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-preview-tts", "displayName": "gemini-2.5-flash-preview-tts", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "tpm": 4000000, "rpm": 10 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 10, "tpm": 4000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "text" ], "output": [ "audio" ] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null, "status": null, "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-flash-preview-tts", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "mode": "audio_speech", "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "tpm": 4000000, "rpm": 10, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-preview-tts", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text Output Audio", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." } }, { "id": "gemini/gemini/gemini-2.5-pro", "slug": "gemini-gemini-gemini-2-5-pro", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-pro", "displayName": "gemini-2.5-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 1.25, "priorityOutputUsdPer1MTokens": 10, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 2.5, "above200kOutputUsdPer1MTokens": 15, "above200kCachedInputUsdPer1MTokens": 0.25, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_priority": 0.00000125, "input_cost_per_token_above_200k_tokens_priority": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "output_cost_per_token_priority": 0.00001, "output_cost_per_token_above_200k_tokens_priority": 0.000015, "rpm": 2000, "tpm": 800000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "service_tier": true, "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions" ], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": "2026-10-16", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_priority": 0.00000125, "input_cost_per_token_above_200k_tokens_priority": 0.0000025, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "output_cost_per_token_priority": 0.00001, "output_cost_per_token_above_200k_tokens_priority": 0.000015, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_service_tier": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Audio, images, video, text, and PDF Output Text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "gemini/gemini/gemini-2.5-computer-use-preview-10-2025", "slug": "gemini-gemini-gemini-2-5-computer-use-preview-10-2025", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-computer-use-preview-10-2025", "displayName": "gemini-2.5-computer-use-preview-10-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 2.5, "above200kOutputUsdPer1MTokens": 15, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "tpm": 800000 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "computer_use": true, "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-computer-use-preview-10-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/computer-use" }, "rawLitellm": { "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "gemini", "max_images_per_prompt": 3000, "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/computer-use", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "tpm": 800000, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-computer-use-preview-10-2025", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Image, text Output Text" } }, { "id": "gemini/gemini/gemini-3-pro-preview", "slug": "gemini-gemini-gemini-3-pro-preview", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3-pro-preview", "displayName": "gemini-3-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5999999999999996, "priorityOutputUsdPer1MTokens": 21.6, "priorityCachedInputUsdPer1MTokens": 0.36, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": "2026-03-09", "status": "retired", "announcementDate": null, "shutdownDate": "2026-03-09", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-3-pro-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "deprecation_date": "2026-03-09", "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "gemini/gemini/gemini-3.1-flash-lite-preview", "slug": "gemini-gemini-gemini-3-1-flash-lite-preview", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3.1-flash-lite-preview", "displayName": "gemini-3.1-flash-lite-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 1.5, "audioInputUsdPer1MTokens": 0.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "rpm": 15, "tpm": 250000, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 15, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": false, "code_execution": true, "file_search": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-3.1-flash-lite-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_code_execution": true, "supports_file_search": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text" } }, { "id": "gemini/gemini/gemini-3.1-flash-lite", "slug": "gemini-gemini-gemini-3-1-flash-lite", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3.1-flash-lite", "displayName": "gemini-3.1-flash-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 1.5, "audioInputUsdPer1MTokens": 0.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.125, "batchOutputUsdPer1MTokens": 0.75, "batchCachedInputUsdPer1MTokens": 0.012499999999999999, "priorityInputUsdPer1MTokens": 0.44999999999999996, "priorityOutputUsdPer1MTokens": 2.7, "priorityCachedInputUsdPer1MTokens": 0.045, "flexInputUsdPer1MTokens": 0.125, "flexOutputUsdPer1MTokens": 0.75, "flexCachedInputUsdPer1MTokens": 0.012499999999999999, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "rpm": 15, "tpm": 250000, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 15, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": false, "code_execution": true, "file_search": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": "2027-05-07", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-3.1-flash-lite", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_code_execution": true, "supports_file_search": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "gemini/gemini/gemini-3-flash-preview", "slug": "gemini-gemini-gemini-3-flash-preview", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3-flash-preview", "displayName": "gemini-3-flash-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 3, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.8999999999999999, "priorityOutputUsdPer1MTokens": 5.4, "priorityCachedInputUsdPer1MTokens": 0.09, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 5e-7, "output_cost_per_reasoning_token": 0.000003, "output_cost_per_token": 0.000003, "rpm": 2000, "tpm": 800000, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-3-flash-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing/gemini-3" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 5e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.000003, "output_cost_per_token": 0.000003, "rpm": 2000, "source": "https://ai.google.dev/pricing/gemini-3", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text" }, "benchmarks": { "swebenchverified_resolved_gemini3flashhighreasoning_benchmarkleaderboard_215": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash (high reasoning)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_gemini3flashpreviewhigh_benchmarkleaderboard_234": { "label": "LiveBench", "category": "general_knowledge", "score": 72.4, "scoreText": "72.40", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash Preview High", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific high-effort variant." } } }, { "id": "gemini/gemini/gemini-3.5-flash", "slug": "gemini-gemini-gemini-3-5-flash", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3.5-flash", "displayName": "gemini-3.5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 9, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 9, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.7, "priorityOutputUsdPer1MTokens": 16.2, "priorityCachedInputUsdPer1MTokens": 0.27, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 0.0000015, "output_cost_per_reasoning_token": 0.000009, "output_cost_per_token": 0.000009, "rpm": 2000, "tpm": 800000, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "audio_input": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-3.5-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing/gemini-3" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 0.0000015, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.000009, "output_cost_per_token": 0.000009, "rpm": 2000, "source": "https://ai.google.dev/pricing/gemini-3", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." }, "benchmarks": { "mmmupro_accuracy_gemini35flashhigh_benchmarkleaderboard_251": { "label": "MMMU-Pro", "category": "multimodal", "score": 84, "scoreText": "84%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.5 Flash", "exactModelOrSnapshot": "Gemini 3.5 Flash (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard top row summarized on the page." }, "mmmupro_accuracy_gemini35flashmedium_benchmarkleaderboard_252": { "label": "MMMU-Pro", "category": "multimodal", "score": 84, "scoreText": "84%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.5 Flash", "exactModelOrSnapshot": "Gemini 3.5 Flash (medium)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard row for the medium variant." } } }, { "id": "gemini/gemini/gemini-3.1-pro-preview", "slug": "gemini-gemini-gemini-3-1-pro-preview", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3.1-pro-preview", "displayName": "gemini-3.1-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5999999999999996, "priorityOutputUsdPer1MTokens": 21.6, "priorityCachedInputUsdPer1MTokens": 0.36, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "url_context": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-3.1-pro-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." }, "benchmarks": { "livebench_livebenchscore_gemini31propreviewhigh_benchmarkleaderboard_229": { "label": "LiveBench", "category": "general_knowledge", "score": 79.93, "scoreText": "79.93", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview High*", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; source notes this row as a high-effort variant." }, "lmarenatextarenaenglish_arenaelo_gemini31propreview_benchmarkleaderboard_240": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1490, "scoreText": "1490±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "gemini-3.1-pro-preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "gpqadiamond_accuracy_gemini31propreview_benchmarkleaderboard_245": { "label": "GPQA Diamond", "category": "science", "score": 94.1, "scoreText": "94.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Top row summarized on the Artificial Analysis GPQA Diamond leaderboard." }, "mmmupro_accuracy_gemini31propreview_benchmarkleaderboard_253": { "label": "MMMU-Pro", "category": "multimodal", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard row shown without a route qualifier." } } }, { "id": "gemini/gemini/gemini-3.1-pro-preview-customtools", "slug": "gemini-gemini-gemini-3-1-pro-preview-customtools", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3.1-pro-preview-customtools", "displayName": "gemini-3.1-pro-preview-customtools", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5999999999999996, "priorityOutputUsdPer1MTokens": 21.6, "priorityCachedInputUsdPer1MTokens": 0.36, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true, "url_context": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-3.1-pro-preview-customtools", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview" ], "manual_model_modalities_note": "Google Gemini exact alias override from version list" }, "benchmarks": { "livebench_livebenchscore_gemini31propreviewhigh_benchmarkleaderboard_229": { "label": "LiveBench", "category": "general_knowledge", "score": 79.93, "scoreText": "79.93", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview High*", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; source notes this row as a high-effort variant." }, "lmarenatextarenaenglish_arenaelo_gemini31propreview_benchmarkleaderboard_240": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1490, "scoreText": "1490±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "gemini-3.1-pro-preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "gpqadiamond_accuracy_gemini31propreview_benchmarkleaderboard_245": { "label": "GPQA Diamond", "category": "science", "score": 94.1, "scoreText": "94.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Top row summarized on the Artificial Analysis GPQA Diamond leaderboard." }, "mmmupro_accuracy_gemini31propreview_benchmarkleaderboard_253": { "label": "MMMU-Pro", "category": "multimodal", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard row shown without a route qualifier." } } }, { "id": "vertex_ai-language-models/gemini-3-flash-preview", "slug": "vertex_ai-language-models-gemini-3-flash-preview", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3-flash-preview", "displayName": "gemini-3-flash-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 3, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.8999999999999999, "priorityOutputUsdPer1MTokens": 5.4, "priorityCachedInputUsdPer1MTokens": 0.09, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 5e-7, "output_cost_per_reasoning_token": 0.000003, "output_cost_per_token": 0.000003, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-3-flash-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing/gemini-3" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 5e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.000003, "output_cost_per_token": 0.000003, "source": "https://ai.google.dev/pricing/gemini-3", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text" }, "benchmarks": { "swebenchverified_resolved_gemini3flashhighreasoning_benchmarkleaderboard_215": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash (high reasoning)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_gemini3flashpreviewhigh_benchmarkleaderboard_234": { "label": "LiveBench", "category": "general_knowledge", "score": 72.4, "scoreText": "72.40", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash Preview High", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific high-effort variant." } } }, { "id": "vertex_ai-language-models/gemini-3.5-flash", "slug": "vertex_ai-language-models-gemini-3-5-flash", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3.5-flash", "displayName": "gemini-3.5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 9, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 9, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.7, "priorityOutputUsdPer1MTokens": 16.2, "priorityCachedInputUsdPer1MTokens": 0.27, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 0.0000015, "output_cost_per_reasoning_token": 0.000009, "output_cost_per_token": 0.000009, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "audio_input": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-3.5-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing/gemini-3" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 0.0000015, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.000009, "output_cost_per_token": 0.000009, "source": "https://ai.google.dev/pricing/gemini-3", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "supports_service_tier": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text" }, "benchmarks": { "mmmupro_accuracy_gemini35flashhigh_benchmarkleaderboard_251": { "label": "MMMU-Pro", "category": "multimodal", "score": 84, "scoreText": "84%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.5 Flash", "exactModelOrSnapshot": "Gemini 3.5 Flash (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard top row summarized on the page." }, "mmmupro_accuracy_gemini35flashmedium_benchmarkleaderboard_252": { "label": "MMMU-Pro", "category": "multimodal", "score": 84, "scoreText": "84%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.5 Flash", "exactModelOrSnapshot": "Gemini 3.5 Flash (medium)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard row for the medium variant." } } }, { "id": "gemini/gemini/gemini-2.5-pro-preview-tts", "slug": "gemini-gemini-gemini-2-5-pro-preview-tts", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-pro-preview-tts", "displayName": "gemini-2.5-pro-preview-tts", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.7, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 2.5, "above200kOutputUsdPer1MTokens": 15, "above200kCachedInputUsdPer1MTokens": 0.25, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 10000, "tpm": 10000000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 10000, "tpm": 10000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "text" ], "input": [ "text" ], "output": [ "audio" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": null, "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-pro-preview-tts", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": false, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "tpm": 10000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro-preview-tts", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text Output Audio", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "gemini/gemini/gemini-exp-1114", "slug": "gemini-gemini-gemini-exp-1114", "provider": "Google", "providerSlug": "gemini", "name": "gemini-exp-1114", "displayName": "gemini-exp-1114", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, "rpm": 1000, "tpm": 4000000 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 1000, "tpm": 4000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-exp-1114", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "metadata": { "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true }, "mode": "chat", "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, "rpm": 1000, "source": "https://ai.google.dev/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "tpm": 4000000 } }, { "id": "gemini/gemini/gemini-exp-1206", "slug": "gemini-gemini-gemini-exp-1206", "provider": "Google", "providerSlug": "gemini", "name": "gemini-exp-1206", "displayName": "gemini-exp-1206", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, "rpm": 1000, "tpm": 4000000 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 2097152, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 1000, "tpm": 4000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-exp-1206", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 2097152, "max_output_tokens": 8192, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "metadata": { "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true }, "mode": "chat", "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, "rpm": 1000, "source": "https://ai.google.dev/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "tpm": 4000000 } }, { "id": "gemini/gemini/gemini-gemma-2-27b-it", "slug": "gemini-gemini-gemini-gemma-2-27b-it", "provider": "Google", "providerSlug": "gemini", "name": "gemini-gemma-2-27b-it", "displayName": "gemini-gemma-2-27b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 1.0499999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.00000105, "tpm": 250000, "rpm": 10 } }, "limits": { "contextWindow": 8192, "maxInputTokens": null, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 10, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-gemma-2-27b-it", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_token": 3.5e-7, "litellm_provider": "gemini", "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000105, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "tpm": 250000, "rpm": 10 }, "benchmarks": { "mmlu_5shottop1_gemma2pt27b_officialmodelcard_189": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "hellaswag_10shot_gemma2pt27b_officialmodelcard_190": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "humaneval_pass1_gemma2pt27b_officialmodelcard_191": { "label": "HumanEval", "category": "coding", "score": 51.8, "scoreText": "51.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "gsm8k_5shotmaj1_gemma2pt27b_officialmodelcard_192": { "label": "GSM8K", "category": "math", "score": 74, "scoreText": "74.0", "metric": "5-shot, maj@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "local_mmlu_5shottop1_gemmapt27b_officialmodelcard_23": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_hellaswag_10shot_gemmapt27b_officialmodelcard_24": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_arcc_25shot_gemmapt27b_officialmodelcard_25": { "label": "ARC-Challenge", "category": "reasoning", "score": 71.4, "scoreText": "71.4", "metric": "25-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_triviaqa_5shot_gemmapt27b_officialmodelcard_26": { "label": "TriviaQA", "category": "general_knowledge", "score": 83.7, "scoreText": "83.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_realtoxicity_average_gemma2it27b_officialmodelcard_27": { "label": "RealToxicity", "category": "safety", "score": 8.84, "scoreText": "8.84", "metric": "average", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." }, "local_truthfulqa_score_gemma2it27b_officialmodelcard_28": { "label": "TruthfulQA", "category": "safety", "score": 51.6, "scoreText": "51.60", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." } } }, { "id": "gemini/gemini/gemini-gemma-2-9b-it", "slug": "gemini-gemini-gemini-gemma-2-9b-it", "provider": "Google", "providerSlug": "gemini", "name": "gemini-gemma-2-9b-it", "displayName": "gemini-gemma-2-9b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 1.0499999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.00000105, "tpm": 250000, "rpm": 10 } }, "limits": { "contextWindow": 8192, "maxInputTokens": null, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 10, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-gemma-2-9b-it", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_token": 3.5e-7, "litellm_provider": "gemini", "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000105, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "tpm": 250000, "rpm": 10 }, "benchmarks": { "mmlu_5shottop1_gemma2pt27b_officialmodelcard_189": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "hellaswag_10shot_gemma2pt27b_officialmodelcard_190": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "humaneval_pass1_gemma2pt27b_officialmodelcard_191": { "label": "HumanEval", "category": "coding", "score": 51.8, "scoreText": "51.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "gsm8k_5shotmaj1_gemma2pt27b_officialmodelcard_192": { "label": "GSM8K", "category": "math", "score": 74, "scoreText": "74.0", "metric": "5-shot, maj@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "local_mmlu_5shottop1_gemmapt27b_officialmodelcard_23": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_hellaswag_10shot_gemmapt27b_officialmodelcard_24": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_arcc_25shot_gemmapt27b_officialmodelcard_25": { "label": "ARC-Challenge", "category": "reasoning", "score": 71.4, "scoreText": "71.4", "metric": "25-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_triviaqa_5shot_gemmapt27b_officialmodelcard_26": { "label": "TriviaQA", "category": "general_knowledge", "score": 83.7, "scoreText": "83.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_realtoxicity_average_gemma2it27b_officialmodelcard_27": { "label": "RealToxicity", "category": "safety", "score": 8.84, "scoreText": "8.84", "metric": "average", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." }, "local_truthfulqa_score_gemma2it27b_officialmodelcard_28": { "label": "TruthfulQA", "category": "safety", "score": 51.6, "scoreText": "51.60", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." } } }, { "id": "gemini/gemini/gemma-3-27b-it", "slug": "gemini-gemini-gemma-3-27b-it", "provider": "Google", "providerSlug": "gemini", "name": "gemma-3-27b-it", "displayName": "gemma-3-27b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0, "perCharacterOutputUsd": 0, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, "input_cost_per_character": 0, "input_cost_per_character_above_128k_tokens": 0, "input_cost_per_image": 0, "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "input_cost_per_video_per_second": 0, "input_cost_per_video_per_second_above_128k_tokens": 0, "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemma-3-27b-it", "syncedAt": "2026-05-28", "sourceUrl": "https://aistudio.google.com" }, "rawLitellm": { "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, "input_cost_per_character": 0, "input_cost_per_character_above_128k_tokens": 0, "input_cost_per_image": 0, "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "input_cost_per_video_per_second": 0, "input_cost_per_video_per_second_above_128k_tokens": 0, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, "source": "https://aistudio.google.com", "supports_audio_output": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "gemini/gemini/imagen-3.0-fast-generate-001", "slug": "gemini-gemini-imagen-3-0-fast-generate-001", "provider": "Google", "providerSlug": "gemini", "name": "imagen-3.0-fast-generate-001", "displayName": "imagen-3.0-fast-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 20000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.02 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/imagen-3.0-fast-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "gemini", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "id": "gemini/gemini/imagen-3.0-generate-001", "slug": "gemini-gemini-imagen-3-0-generate-001", "provider": "Google", "providerSlug": "gemini", "name": "imagen-3.0-generate-001", "displayName": "imagen-3.0-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/imagen-3.0-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "gemini", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "id": "gemini/gemini/imagen-3.0-generate-002", "slug": "gemini-gemini-imagen-3-0-generate-002", "provider": "Google", "providerSlug": "gemini", "name": "imagen-3.0-generate-002", "displayName": "imagen-3.0-generate-002", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": "2025-11-10", "status": "retired", "announcementDate": null, "shutdownDate": "2025-11-10", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/imagen-3.0-generate-002", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "deprecation_date": "2025-11-10", "litellm_provider": "gemini", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "gemini/gemini/imagen-4.0-fast-generate-001", "slug": "gemini-gemini-imagen-4-0-fast-generate-001", "provider": "Google", "providerSlug": "gemini", "name": "imagen-4.0-fast-generate-001", "displayName": "imagen-4.0-fast-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 20000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.02 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "text" ], "output": [ "image" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": "2026-06-24", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/imagen-4.0-fast-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "gemini", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/imagen", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Text Output Images", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "gemini/gemini/imagen-4.0-generate-001", "slug": "gemini-gemini-imagen-4-0-generate-001", "provider": "Google", "providerSlug": "gemini", "name": "imagen-4.0-generate-001", "displayName": "imagen-4.0-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "text" ], "output": [ "image" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": "2026-06-24", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/imagen-4.0-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "gemini", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/imagen", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Text Output Images", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "gemini/gemini/imagen-4.0-ultra-generate-001", "slug": "gemini-gemini-imagen-4-0-ultra-generate-001", "provider": "Google", "providerSlug": "gemini", "name": "imagen-4.0-ultra-generate-001", "displayName": "imagen-4.0-ultra-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "text" ], "output": [ "image" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": "2026-06-24", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/imagen-4.0-ultra-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "gemini", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/imagen", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Text Output Images", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "gemini/gemini/learnlm-1.5-pro-experimental", "slug": "gemini-gemini-learnlm-1-5-pro-experimental", "provider": "Google", "providerSlug": "gemini", "name": "learnlm-1.5-pro-experimental", "displayName": "learnlm-1.5-pro-experimental", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0, "perCharacterOutputUsd": 0, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, "input_cost_per_character": 0, "input_cost_per_character_above_128k_tokens": 0, "input_cost_per_image": 0, "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "input_cost_per_video_per_second": 0, "input_cost_per_video_per_second_above_128k_tokens": 0, "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32767, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/learnlm-1.5-pro-experimental", "syncedAt": "2026-05-28", "sourceUrl": "https://aistudio.google.com" }, "rawLitellm": { "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, "input_cost_per_character": 0, "input_cost_per_character_above_128k_tokens": 0, "input_cost_per_image": 0, "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "input_cost_per_video_per_second": 0, "input_cost_per_video_per_second_above_128k_tokens": 0, "litellm_provider": "gemini", "max_input_tokens": 32767, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, "source": "https://aistudio.google.com", "supports_audio_output": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "gemini/gemini/lyria-3-clip-preview", "slug": "gemini-gemini-lyria-3-clip-preview", "provider": "Google", "providerSlug": "gemini", "name": "lyria-3-clip-preview", "displayName": "lyria-3-clip-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_image": 0.04, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": false, "audio_output": true, "function_calling": false, "prompt_caching": false, "response_schema": false, "system_messages": false, "vision": false, "web_search": false } }, "modalities": { "supported": [ "audio", "image", "text" ], "input": [ "image", "text" ], "output": [ "audio", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/lyria-3-clip-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_input": false, "supports_audio_output": true, "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_web_search": false, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/lyria-3-pro-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text and Image Output Audio (MP3), Text (Lyrics)", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." } }, { "id": "gemini/gemini/lyria-3-pro-preview", "slug": "gemini-gemini-lyria-3-pro-preview", "provider": "Google", "providerSlug": "gemini", "name": "lyria-3-pro-preview", "displayName": "lyria-3-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": false, "audio_output": true, "function_calling": false, "prompt_caching": false, "response_schema": false, "system_messages": false, "vision": false, "web_search": false } }, "modalities": { "supported": [ "audio", "image", "text" ], "input": [ "image", "text" ], "output": [ "audio", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/lyria-3-pro-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_input": false, "supports_audio_output": true, "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_web_search": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/lyria-3-pro-preview" ], "manual_model_modalities_note": "Google Lyria exact alias override from model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." } }, { "id": "gemini/gemini/veo-2.0-generate-001", "slug": "gemini-gemini-veo-2-0-generate-001", "provider": "Google", "providerSlug": "gemini", "name": "veo-2.0-generate-001", "displayName": "veo-2.0-generate-001", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.35, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.35 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text" ], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": null, "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists this entry as 'Coming soon' instead of a fixed shutdown date." }, "source": { "type": "litellm", "litellmKey": "gemini/veo-2.0-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/video" }, "rawLitellm": { "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.35, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/veo-2.0-generate-001", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Text, image Output Video", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists this entry as 'Coming soon' instead of a fixed shutdown date." } }, { "id": "gemini/gemini/veo-3.1-fast-generate-preview", "slug": "gemini-gemini-veo-3-1-fast-generate-preview", "provider": "Google", "providerSlug": "gemini", "name": "veo-3.1-fast-generate-preview", "displayName": "veo-3.1-fast-generate-preview", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.15, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.15 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "image", "text" ], "output": [ "audio", "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/veo-3.1-fast-generate-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/video" }, "rawLitellm": { "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.15, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/veo-3.1-generate-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Text, Image Output Video with audio", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." } }, { "id": "gemini/gemini/veo-3.1-generate-preview", "slug": "gemini-gemini-veo-3-1-generate-preview", "provider": "Google", "providerSlug": "gemini", "name": "veo-3.1-generate-preview", "displayName": "veo-3.1-generate-preview", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.4, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.4 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "image", "text" ], "output": [ "audio", "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "active", "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/veo-3.1-generate-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/video" }, "rawLitellm": { "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/veo-3.1-generate-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Text, Image Output Video with audio", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." } }, { "id": "gemini/gemini/veo-3.1-lite-generate-preview", "slug": "gemini-gemini-veo-3-1-lite-generate-preview", "provider": "Google", "providerSlug": "gemini", "name": "veo-3.1-lite-generate-preview", "displayName": "veo-3.1-lite-generate-preview", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.05, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "image", "text" ], "output": [ "audio", "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": null, "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/veo-3.1-lite-generate-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/video" }, "rawLitellm": { "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/veo-3.1-lite-generate-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Input Text, Image Output Video with audio", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." } }, { "id": "gemini/gemini/veo-3.1-fast-generate-001", "slug": "gemini-gemini-veo-3-1-fast-generate-001", "provider": "Google", "providerSlug": "gemini", "name": "veo-3.1-fast-generate-001", "displayName": "veo-3.1-fast-generate-001", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.15, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.15 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/veo-3.1-fast-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/video" }, "rawLitellm": { "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.15, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] } }, { "id": "gemini/gemini/veo-3.1-generate-001", "slug": "gemini-gemini-veo-3-1-generate-001", "provider": "Google", "providerSlug": "gemini", "name": "veo-3.1-generate-001", "displayName": "veo-3.1-generate-001", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.4, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.4 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/veo-3.1-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/video" }, "rawLitellm": { "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] } }, { "id": "github_copilot/github_copilot/claude-haiku-4.5", "slug": "github_copilot-github_copilot-claude-haiku-4-5", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "claude-haiku-4.5", "displayName": "claude-haiku-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16000, "maxInputTokens": 128000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/claude-haiku-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.claude.com/docs/en/about-claude/models/overview" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "github_copilot/github_copilot/claude-opus-4.5", "slug": "github_copilot-github_copilot-claude-opus-4-5", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "claude-opus-4.5", "displayName": "claude-opus-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16000, "maxInputTokens": 128000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/claude-opus-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "github_copilot/github_copilot/claude-opus-4.6-fast", "slug": "github_copilot-github_copilot-claude-opus-4-6-fast", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "claude-opus-4.6-fast", "displayName": "claude-opus-4.6-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16000, "maxInputTokens": 128000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/claude-opus-4.6-fast", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.claude.com/docs/en/about-claude/models/overview" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "github_copilot/github_copilot/claude-opus-41", "slug": "github_copilot-github_copilot-claude-opus-41", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "claude-opus-41", "displayName": "claude-opus-41", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16000, "maxInputTokens": 80000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/claude-opus-41", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 80000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "github_copilot/github_copilot/claude-sonnet-4", "slug": "github_copilot-github_copilot-claude-sonnet-4", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "claude-sonnet-4", "displayName": "claude-sonnet-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16000, "maxInputTokens": 128000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/claude-sonnet-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "github_copilot/github_copilot/claude-sonnet-4.5", "slug": "github_copilot-github_copilot-claude-sonnet-4-5", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "claude-sonnet-4.5", "displayName": "claude-sonnet-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16000, "maxInputTokens": 128000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/claude-sonnet-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.claude.com/docs/en/about-claude/models/whats-new-claude-4-5" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "github_copilot/github_copilot/gemini-2.5-pro", "slug": "github_copilot-github_copilot-gemini-2-5-pro", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gemini-2.5-pro", "displayName": "gemini-2.5-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gemini-2.5-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://ai.google.dev/gemini-api/docs/models/gemini-v2" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "github_copilot/github_copilot/gemini-3-pro-preview", "slug": "github_copilot-github_copilot-gemini-3-pro-preview", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gemini-3-pro-preview", "displayName": "gemini-3-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gemini-3-pro-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://ai.google.dev/models/gemini" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "github_copilot/github_copilot/gpt-3.5-turbo", "slug": "github_copilot-github_copilot-gpt-3-5-turbo", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-3.5-turbo", "displayName": "gpt-3.5-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-3.5-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.openai.com/docs/models/gpt-3.5-turbo" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" } }, { "id": "github_copilot/github_copilot/gpt-3.5-turbo-0613", "slug": "github_copilot-github_copilot-gpt-3-5-turbo-0613", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-3.5-turbo-0613", "displayName": "gpt-3.5-turbo-0613", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-3.5-turbo-0613", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.openai.com/docs/pricing", "https://platform.openai.com/docs/deprecations" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" } }, { "id": "github_copilot/github_copilot/gpt-4", "slug": "github_copilot-github_copilot-gpt-4", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4", "displayName": "gpt-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.openai.com/docs/models/gpt-4" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" } }, { "id": "github_copilot/github_copilot/gpt-4-0613", "slug": "github_copilot-github_copilot-gpt-4-0613", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4-0613", "displayName": "gpt-4-0613", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4-0613", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.openai.com/docs/models/gpt-4" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" } }, { "id": "github_copilot/github_copilot/gpt-4-o-preview", "slug": "github_copilot-github_copilot-gpt-4-o-preview", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4-o-preview", "displayName": "gpt-4-o-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 64000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4-o-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true } }, { "id": "github_copilot/github_copilot/gpt-4.1", "slug": "github_copilot-github_copilot-gpt-4-1", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4.1", "displayName": "gpt-4.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.openai.com/docs/models/gpt-4.1" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "github_copilot/github_copilot/gpt-4.1-2025-04-14", "slug": "github_copilot-github_copilot-gpt-4-1-2025-04-14", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4.1-2025-04-14", "displayName": "gpt-4.1-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4.1-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.openai.com/docs/models/gpt-4.1" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "github_copilot/github_copilot/gpt-41-copilot", "slug": "github_copilot-github_copilot-gpt-41-copilot", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-41-copilot", "displayName": "gpt-41-copilot", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-41-copilot", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "mode": "completion" } }, { "id": "github_copilot/github_copilot/gpt-4o", "slug": "github_copilot-github_copilot-gpt-4o", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4o", "displayName": "gpt-4o", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 64000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4o", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.openai.com/docs/models/gpt-4o" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "github_copilot/github_copilot/gpt-4o-2024-05-13", "slug": "github_copilot-github_copilot-gpt-4o-2024-05-13", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4o-2024-05-13", "displayName": "gpt-4o-2024-05-13", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 64000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4o-2024-05-13", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://platform.openai.com/docs/models/gpt-4o" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "github_copilot/github_copilot/gpt-4o-2024-08-06", "slug": "github_copilot-github_copilot-gpt-4o-2024-08-06", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4o-2024-08-06", "displayName": "gpt-4o-2024-08-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16384, "maxInputTokens": 64000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4o-2024-08-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.openai.com/docs/models/gpt-4o" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "github_copilot/github_copilot/gpt-4o-2024-11-20", "slug": "github_copilot-github_copilot-gpt-4o-2024-11-20", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4o-2024-11-20", "displayName": "gpt-4o-2024-11-20", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16384, "maxInputTokens": 64000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4o-2024-11-20", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.openai.com/docs/models/gpt-4o" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "github_copilot/github_copilot/gpt-4o-mini", "slug": "github_copilot-github_copilot-gpt-4o-mini", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4o-mini", "displayName": "gpt-4o-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 64000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4o-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.openai.com/docs/models/gpt-4o-mini" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "github_copilot/github_copilot/gpt-4o-mini-2024-07-18", "slug": "github_copilot-github_copilot-gpt-4o-mini-2024-07-18", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-4o-mini-2024-07-18", "displayName": "gpt-4o-mini-2024-07-18", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4096, "maxInputTokens": 64000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-4o-mini-2024-07-18", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.openai.com/docs/models/gpt-4o-mini" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "github_copilot/github_copilot/gpt-5", "slug": "github_copilot-github_copilot-gpt-5", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-5", "displayName": "gpt-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.openai.com/docs/models/gpt-5" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "github_copilot/github_copilot/gpt-5-mini", "slug": "github_copilot-github_copilot-gpt-5-mini", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-5-mini", "displayName": "gpt-5-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-5-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.openai.com/docs/models/gpt-5-mini" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "github_copilot/github_copilot/gpt-5.1", "slug": "github_copilot-github_copilot-gpt-5-1", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-5.1", "displayName": "gpt-5.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-5.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/concepts/fedramp-models", "https://platform.openai.com/docs/models/gpt-5.1" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "github_copilot/github_copilot/gpt-5.1-codex-max", "slug": "github_copilot-github_copilot-gpt-5-1-codex-max", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-5.1-codex-max", "displayName": "gpt-5.1-codex-max", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-5.1-codex-max", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "github_copilot/github_copilot/gpt-5.2", "slug": "github_copilot-github_copilot-gpt-5-2", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-5.2", "displayName": "gpt-5.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-5.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.github.com/en/copilot/reference/ai-models/supported-models", "https://platform.openai.com/docs/models/gpt-5.2" ], "manual_model_modalities_note": "GitHub Copilot exact supported-model id from official docs" }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "github_copilot/github_copilot/gpt-5.3-codex", "slug": "github_copilot-github_copilot-gpt-5-3-codex", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "gpt-5.3-codex", "displayName": "gpt-5.3-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/gpt-5.3-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true } }, { "id": "github_copilot/github_copilot/text-embedding-3-small", "slug": "github_copilot-github_copilot-text-embedding-3-small", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "text-embedding-3-small", "displayName": "text-embedding-3-small", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/text-embedding-3-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding" } }, { "id": "github_copilot/github_copilot/text-embedding-3-small-inference", "slug": "github_copilot-github_copilot-text-embedding-3-small-inference", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "text-embedding-3-small-inference", "displayName": "text-embedding-3-small-inference", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/text-embedding-3-small-inference", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding" } }, { "id": "github_copilot/github_copilot/text-embedding-ada-002", "slug": "github_copilot-github_copilot-text-embedding-ada-002", "provider": "github_copilot", "providerSlug": "github_copilot", "name": "text-embedding-ada-002", "displayName": "text-embedding-ada-002", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "github_copilot/text-embedding-ada-002", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding" } }, { "id": "chatgpt/chatgpt/gpt-5.4", "slug": "chatgpt-chatgpt-gpt-5-4", "provider": "chatgpt", "providerSlug": "chatgpt", "name": "gpt-5.4", "displayName": "gpt-5.4", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt/gpt-5.4", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "benchmarks": { "livebench_livebenchscore_gpt54thinkingxhigheffort_benchmarkleaderboard_228": { "label": "LiveBench", "category": "general_knowledge", "score": 80.28, "scoreText": "80.28", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "GPT-5.4 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt54high_benchmarkleaderboard_244": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1483, "scoreText": "1483±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "gpt-5.4-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." } } }, { "id": "chatgpt/chatgpt/gpt-5.4-pro", "slug": "chatgpt-chatgpt-gpt-5-4-pro", "provider": "chatgpt", "providerSlug": "chatgpt", "name": "gpt-5.4-pro", "displayName": "gpt-5.4-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt/gpt-5.4-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true } }, { "id": "chatgpt/chatgpt/gpt-5.3-codex", "slug": "chatgpt-chatgpt-gpt-5-3-codex", "provider": "chatgpt", "providerSlug": "chatgpt", "name": "gpt-5.3-codex", "displayName": "gpt-5.3-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt/gpt-5.3-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true } }, { "id": "chatgpt/chatgpt/gpt-5.3-codex-spark", "slug": "chatgpt-chatgpt-gpt-5-3-codex-spark", "provider": "chatgpt", "providerSlug": "chatgpt", "name": "gpt-5.3-codex-spark", "displayName": "gpt-5.3-codex-spark", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt/gpt-5.3-codex-spark", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true } }, { "id": "chatgpt/chatgpt/gpt-5.3-instant", "slug": "chatgpt-chatgpt-gpt-5-3-instant", "provider": "chatgpt", "providerSlug": "chatgpt", "name": "gpt-5.3-instant", "displayName": "gpt-5.3-instant", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt/gpt-5.3-instant", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true } }, { "id": "chatgpt/chatgpt/gpt-5.3-chat-latest", "slug": "chatgpt-chatgpt-gpt-5-3-chat-latest", "provider": "chatgpt", "providerSlug": "chatgpt", "name": "gpt-5.3-chat-latest", "displayName": "gpt-5.3-chat-latest", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt/gpt-5.3-chat-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true } }, { "id": "chatgpt/chatgpt/gpt-5.2-codex", "slug": "chatgpt-chatgpt-gpt-5-2-codex", "provider": "chatgpt", "providerSlug": "chatgpt", "name": "gpt-5.2-codex", "displayName": "gpt-5.2-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt/gpt-5.2-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "chatgpt/chatgpt/gpt-5.2", "slug": "chatgpt-chatgpt-gpt-5-2", "provider": "chatgpt", "providerSlug": "chatgpt", "name": "gpt-5.2", "displayName": "gpt-5.2", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt/gpt-5.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "chatgpt/chatgpt/gpt-5.1-codex-max", "slug": "chatgpt-chatgpt-gpt-5-1-codex-max", "provider": "chatgpt", "providerSlug": "chatgpt", "name": "gpt-5.1-codex-max", "displayName": "gpt-5.1-codex-max", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt/gpt-5.1-codex-max", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "chatgpt/chatgpt/gpt-5.1-codex-mini", "slug": "chatgpt-chatgpt-gpt-5-1-codex-mini", "provider": "chatgpt", "providerSlug": "chatgpt", "name": "gpt-5.1-codex-mini", "displayName": "gpt-5.1-codex-mini", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt/gpt-5.1-codex-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "gigachat/gigachat/GigaChat-2-Lite", "slug": "gigachat-gigachat-gigachat-2-lite", "provider": "gigachat", "providerSlug": "gigachat", "name": "GigaChat-2-Lite", "displayName": "GigaChat-2-Lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gigachat/GigaChat-2-Lite", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_system_messages": true } }, { "id": "gigachat/gigachat/GigaChat-2-Max", "slug": "gigachat-gigachat-gigachat-2-max", "provider": "gigachat", "providerSlug": "gigachat", "name": "GigaChat-2-Max", "displayName": "GigaChat-2-Max", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gigachat/GigaChat-2-Max", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true } }, { "id": "gigachat/gigachat/GigaChat-2-Pro", "slug": "gigachat-gigachat-gigachat-2-pro", "provider": "gigachat", "providerSlug": "gigachat", "name": "GigaChat-2-Pro", "displayName": "GigaChat-2-Pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gigachat/GigaChat-2-Pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true } }, { "id": "gigachat/gigachat/Embeddings", "slug": "gigachat-gigachat-embeddings", "provider": "gigachat", "providerSlug": "gigachat", "name": "Embeddings", "displayName": "Embeddings", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gigachat/Embeddings", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "gigachat", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024 } }, { "id": "gigachat/gigachat/Embeddings-2", "slug": "gigachat-gigachat-embeddings-2", "provider": "gigachat", "providerSlug": "gigachat", "name": "Embeddings-2", "displayName": "Embeddings-2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gigachat/Embeddings-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "gigachat", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024 } }, { "id": "gigachat/gigachat/EmbeddingsGigaR", "slug": "gigachat-gigachat-embeddingsgigar", "provider": "gigachat", "providerSlug": "gigachat", "name": "EmbeddingsGigaR", "displayName": "EmbeddingsGigaR", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": null, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 2560, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gigachat/EmbeddingsGigaR", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "gigachat", "max_input_tokens": 4096, "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 2560 } }, { "id": "gmi/gmi/anthropic/claude-opus-4.5", "slug": "gmi-gmi-anthropic-claude-opus-4-5", "provider": "gmi", "providerSlug": "gmi", "name": "claude-opus-4.5", "displayName": "claude-opus-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 409600, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/anthropic/claude-opus-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000025, "supports_function_calling": true, "supports_vision": true, "supports_minimal_reasoning_effort": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "gmi/gmi/anthropic/claude-sonnet-4.5", "slug": "gmi-gmi-anthropic-claude-sonnet-4-5", "provider": "gmi", "providerSlug": "gmi", "name": "claude-sonnet-4.5", "displayName": "claude-sonnet-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 409600, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/anthropic/claude-sonnet-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_vision": true }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "gmi/gmi/anthropic/claude-sonnet-4", "slug": "gmi-gmi-anthropic-claude-sonnet-4", "provider": "gmi", "providerSlug": "gmi", "name": "claude-sonnet-4", "displayName": "claude-sonnet-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 409600, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/anthropic/claude-sonnet-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_vision": true }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "gmi/gmi/anthropic/claude-opus-4", "slug": "gmi-gmi-anthropic-claude-opus-4", "provider": "gmi", "providerSlug": "gmi", "name": "claude-opus-4", "displayName": "claude-opus-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 409600, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/anthropic/claude-opus-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "supports_function_calling": true, "supports_vision": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "gmi/gmi/openai/gpt-5.2", "slug": "gmi-gmi-openai-gpt-5-2", "provider": "gmi", "providerSlug": "gmi", "name": "gpt-5.2", "displayName": "gpt-5.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 409600, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/openai/gpt-5.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000175, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000014, "supports_function_calling": true }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "gmi/gmi/openai/gpt-5.1", "slug": "gmi-gmi-openai-gpt-5-1", "provider": "gmi", "providerSlug": "gmi", "name": "gpt-5.1", "displayName": "gpt-5.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 409600, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/openai/gpt-5.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000125, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "gmi/gmi/openai/gpt-5", "slug": "gmi-gmi-openai-gpt-5", "provider": "gmi", "providerSlug": "gmi", "name": "gpt-5", "displayName": "gpt-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 409600, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/openai/gpt-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000125, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "gmi/gmi/openai/gpt-4o", "slug": "gmi-gmi-openai-gpt-4o", "provider": "gmi", "providerSlug": "gmi", "name": "gpt-4o", "displayName": "gpt-4o", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 131072, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/openai/gpt-4o", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "gmi/gmi/openai/gpt-4o-mini", "slug": "gmi-gmi-openai-gpt-4o-mini", "provider": "gmi", "providerSlug": "gmi", "name": "gpt-4o-mini", "displayName": "gpt-4o-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 131072, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/openai/gpt-4o-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_vision": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "gmi/gmi/deepseek-ai/DeepSeek-V3.2", "slug": "gmi-gmi-deepseek-ai-deepseek-v3-2", "provider": "gmi", "providerSlug": "gmi", "name": "DeepSeek-V3.2", "displayName": "DeepSeek-V3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.28, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.28, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 163840, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/deepseek-ai/DeepSeek-V3.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.8e-7, "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-7, "supports_function_calling": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "gmi/gmi/deepseek-ai/DeepSeek-V3-0324", "slug": "gmi-gmi-deepseek-ai-deepseek-v3-0324", "provider": "gmi", "providerSlug": "gmi", "name": "DeepSeek-V3-0324", "displayName": "DeepSeek-V3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.28, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.28, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.8e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 163840, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/deepseek-ai/DeepSeek-V3-0324", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.8e-7, "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-7, "supports_function_calling": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "gmi/gmi/google/gemini-3-pro-preview", "slug": "gmi-gmi-google-gemini-3-pro-preview", "provider": "gmi", "providerSlug": "gmi", "name": "gemini-3-pro-preview", "displayName": "gemini-3-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/google/gemini-3-pro-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "gmi", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.000012, "supports_function_calling": true, "supports_vision": true }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "gmi/gmi/google/gemini-3-flash-preview", "slug": "gmi-gmi-google-gemini-3-flash-preview", "provider": "gmi", "providerSlug": "gmi", "name": "gemini-3-flash-preview", "displayName": "gemini-3-flash-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/google/gemini-3-flash-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "gmi", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_vision": true }, "benchmarks": { "swebenchverified_resolved_gemini3flashhighreasoning_benchmarkleaderboard_215": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash (high reasoning)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_gemini3flashpreviewhigh_benchmarkleaderboard_234": { "label": "LiveBench", "category": "general_knowledge", "score": 72.4, "scoreText": "72.40", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash Preview High", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific high-effort variant." } } }, { "id": "gmi/gmi/moonshotai/Kimi-K2-Thinking", "slug": "gmi-gmi-moonshotai-kimi-k2-thinking", "provider": "gmi", "providerSlug": "gmi", "name": "Kimi-K2-Thinking", "displayName": "Kimi-K2-Thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 262144, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/moonshotai/Kimi-K2-Thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000012 } }, { "id": "gmi/gmi/MiniMaxAI/MiniMax-M2.1", "slug": "gmi-gmi-minimaxai-minimax-m2-1", "provider": "gmi", "providerSlug": "gmi", "name": "MiniMax-M2.1", "displayName": "MiniMax-M2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 196608, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/MiniMaxAI/MiniMax-M2.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "gmi", "max_input_tokens": 196608, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000012 }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "baseten/baseten/MiniMaxAI/MiniMax-M2.5", "slug": "baseten-baseten-minimaxai-minimax-m2-5", "provider": "baseten", "providerSlug": "baseten", "name": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/MiniMaxAI/MiniMax-M2.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 0.0000012 }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "baseten/baseten/nvidia/Nemotron-120B-A12B", "slug": "baseten-baseten-nvidia-nemotron-120b-a12b", "provider": "baseten", "providerSlug": "baseten", "name": "Nemotron-120B-A12B", "displayName": "Nemotron-120B-A12B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 7.5e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/nvidia/Nemotron-120B-A12B", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 7.5e-7 }, "benchmarks": { "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "baseten/baseten/zai-org/GLM-5", "slug": "baseten-baseten-zai-org-glm-5", "provider": "baseten", "providerSlug": "baseten", "name": "GLM-5", "displayName": "GLM-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.95, "outputUsdPer1MTokens": 3.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.95, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.00000315 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/zai-org/GLM-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9.5e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 0.00000315 }, "benchmarks": { "hle_score_glm5_officialmodelcard_165": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 30.5, "scoreText": "30.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "gpqadiamond_score_glm5_officialmodelcard_166": { "label": "GPQA Diamond", "category": "reasoning", "score": 86, "scoreText": "86.0", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchverified_score_glm5_officialmodelcard_167": { "label": "SWE-bench Verified", "category": "coding", "score": 77.8, "scoreText": "77.8", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "baseten/baseten/zai-org/GLM-4.7", "slug": "baseten-baseten-zai-org-glm-4-7", "provider": "baseten", "providerSlug": "baseten", "name": "GLM-4.7", "displayName": "GLM-4.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/zai-org/GLM-4.7", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 0.0000022 }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "baseten/baseten/zai-org/GLM-4.6", "slug": "baseten-baseten-zai-org-glm-4-6", "provider": "baseten", "providerSlug": "baseten", "name": "GLM-4.6", "displayName": "GLM-4.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/zai-org/GLM-4.6", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 0.0000022 }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_zaiglm46_benchmarkleaderboard_282": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_zaiglm46_benchmarkleaderboard_283": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_zaiglm46_benchmarkleaderboard_284": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_zaiglm46_benchmarkleaderboard_285": { "label": "GPQA Diamond", "category": "reasoning", "score": 78, "scoreText": "78.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_artificialanalysisintelligenceindex_score_zaiglm46_benchmarkleaderboard_310": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysiscodingindex_score_zaiglm46_benchmarkleaderboard_311": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysisagenticindex_score_zaiglm46_benchmarkleaderboard_312": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." } } }, { "id": "baseten/baseten/moonshotai/Kimi-K2.5", "slug": "baseten-baseten-moonshotai-kimi-k2-5", "provider": "baseten", "providerSlug": "baseten", "name": "Kimi-K2.5", "displayName": "Kimi-K2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/moonshotai/Kimi-K2.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 0.000003 }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "baseten/baseten/moonshotai/Kimi-K2-Thinking", "slug": "baseten-baseten-moonshotai-kimi-k2-thinking", "provider": "baseten", "providerSlug": "baseten", "name": "Kimi-K2-Thinking", "displayName": "Kimi-K2-Thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/moonshotai/Kimi-K2-Thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 0.0000025 } }, { "id": "baseten/baseten/moonshotai/Kimi-K2-Instruct-0905", "slug": "baseten-baseten-moonshotai-kimi-k2-instruct-0905", "provider": "baseten", "providerSlug": "baseten", "name": "Kimi-K2-Instruct-0905", "displayName": "Kimi-K2-Instruct-0905", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/moonshotai/Kimi-K2-Instruct-0905", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 0.0000025 } }, { "id": "baseten/baseten/openai/gpt-oss-120b", "slug": "baseten-baseten-openai-gpt-oss-120b", "provider": "baseten", "providerSlug": "baseten", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/openai/gpt-oss-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 5e-7 }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "baseten/baseten/deepseek-ai/DeepSeek-V3.1", "slug": "baseten-baseten-deepseek-ai-deepseek-v3-1", "provider": "baseten", "providerSlug": "baseten", "name": "DeepSeek-V3.1", "displayName": "DeepSeek-V3.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/deepseek-ai/DeepSeek-V3.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 0.0000015 }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "baseten/baseten/deepseek-ai/DeepSeek-V3-0324", "slug": "baseten-baseten-deepseek-ai-deepseek-v3-0324", "provider": "baseten", "providerSlug": "baseten", "name": "DeepSeek-V3-0324", "displayName": "DeepSeek-V3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.77, "outputUsdPer1MTokens": 0.77, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.77, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.7e-7, "output_cost_per_token": 7.7e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "baseten/deepseek-ai/DeepSeek-V3-0324", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.7e-7, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 7.7e-7 }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "gmi/gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", "slug": "gmi-gmi-qwen-qwen3-vl-235b-a22b-instruct-fp8", "provider": "gmi", "providerSlug": "gmi", "name": "Qwen3-VL-235B-A22B-Instruct-FP8", "displayName": "Qwen3-VL-235B-A22B-Instruct-FP8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000014 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 262144, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000014, "supports_vision": true } }, { "id": "gmi/gmi/zai-org/GLM-4.7-FP8", "slug": "gmi-gmi-zai-org-glm-4-7-fp8", "provider": "gmi", "providerSlug": "gmi", "name": "GLM-4.7-FP8", "displayName": "GLM-4.7-FP8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 202752, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gmi/zai-org/GLM-4.7-FP8", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "gmi", "max_input_tokens": 202752, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000002 }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "bedrock_converse/google.gemma-3-12b-it", "slug": "bedrock_converse-google-gemma-3-12b-it", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "google.gemma-3-12b-it", "displayName": "google.gemma-3-12b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.29, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 2.9e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "image", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "google.gemma-3-12b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.9e-7, "supports_system_messages": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-google-gemma-3-12b-it.html" ], "manual_model_modalities_note": "Bedrock Converse exact Google route id from official docs" }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "bedrock_converse/google.gemma-3-27b-it", "slug": "bedrock_converse-google-gemma-3-27b-it", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "google.gemma-3-27b-it", "displayName": "google.gemma-3-27b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22999999999999998, "outputUsdPer1MTokens": 0.38, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.3e-7, "output_cost_per_token": 3.8e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "image", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "google.gemma-3-27b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.8e-7, "supports_system_messages": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-google-gemma-3-27b-pt.html" ], "manual_model_modalities_note": "Bedrock Converse exact Google route id from official docs" }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "bedrock_converse/google.gemma-3-4b-it", "slug": "bedrock_converse-google-gemma-3-4b-it", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "google.gemma-3-4b-it", "displayName": "google.gemma-3-4b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "image", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "google.gemma-3-4b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-8, "supports_system_messages": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-google-gemma-3-4b-it.html" ], "manual_model_modalities_note": "Bedrock Converse exact Google route id from official docs" }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "google_pse/google_pse/search", "slug": "google_pse-google_pse-search", "provider": "google_pse", "providerSlug": "google_pse", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 5, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "google_pse/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.005, "litellm_provider": "google_pse", "mode": "search", "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "bedrock_converse/global.anthropic.claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock_converse-global-anthropic-claude-sonnet-4-5-20250929-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock_converse/global.anthropic.claude-sonnet-4-20250514-v1:0", "slug": "bedrock_converse-global-anthropic-claude-sonnet-4-20250514-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "global.anthropic.claude-sonnet-4-20250514-v1:0", "displayName": "global.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "global.anthropic.claude-sonnet-4-20250514-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "bedrock_converse/global.anthropic.claude-haiku-4-5-20251001-v1:0", "slug": "bedrock_converse-global-anthropic-claude-haiku-4-5-20251001-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": 1.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock_converse/global.amazon.nova-2-lite-v1:0", "slug": "bedrock_converse-global-amazon-nova-2-lite-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "global.amazon.nova-2-lite-v1:0", "displayName": "global.amazon.nova-2-lite-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "video_input": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "global.amazon.nova-2-lite-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000025, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_video_input": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-lite.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "openai/gpt-3.5-turbo", "slug": "openai-gpt-3-5-turbo", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-3.5-turbo", "displayName": "gpt-3.5-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "OpenAI docs explicitly list this alias with gpt-3.5-turbo-0125." }, "source": { "type": "litellm", "litellmKey": "gpt-3.5-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-3.5-turbo" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "OpenAI docs explicitly list this alias with gpt-3.5-turbo-0125." } }, { "id": "openai/gpt-3.5-turbo-0125", "slug": "openai-gpt-3-5-turbo-0125", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-3.5-turbo-0125", "displayName": "gpt-3.5-turbo-0125", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-3.5-turbo-0125", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-3.5-turbo" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "openai/gpt-3.5-turbo-1106", "slug": "openai-gpt-3-5-turbo-1106", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-3.5-turbo-1106", "displayName": "gpt-3.5-turbo-1106", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-09-28", "status": "deprecated", "announcementDate": "2025-09-26", "shutdownDate": "2026-09-28", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-3.5-turbo-1106", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-09-28", "input_cost_per_token": 0.000001, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-3.5-turbo" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "openai/gpt-3.5-turbo-16k", "slug": "openai-gpt-3-5-turbo-16k", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-3.5-turbo-16k", "displayName": "gpt-3.5-turbo-16k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "prompt_caching": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-3.5-turbo-16k", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000004, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "text-completion-openai/gpt-3.5-turbo-instruct", "slug": "text-completion-openai-gpt-3-5-turbo-instruct", "provider": "text-completion-openai", "providerSlug": "text-completion-openai", "name": "gpt-3.5-turbo-instruct", "displayName": "gpt-3.5-turbo-instruct", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-3.5-turbo-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000015, "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.000002 } }, { "id": "text-completion-openai/gpt-3.5-turbo-instruct-0914", "slug": "text-completion-openai-gpt-3-5-turbo-instruct-0914", "provider": "text-completion-openai", "providerSlug": "text-completion-openai", "name": "gpt-3.5-turbo-instruct-0914", "displayName": "gpt-3.5-turbo-instruct-0914", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4097, "maxInputTokens": 8192, "maxOutputTokens": 4097, "maxTokens": 4097, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-3.5-turbo-instruct-0914", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000015, "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4097, "max_tokens": 4097, "mode": "completion", "output_cost_per_token": 0.000002 } }, { "id": "openai/gpt-4", "slug": "openai-gpt-4", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4", "displayName": "gpt-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "OpenAI docs explicitly list this alias with gpt-4-0613." }, "source": { "type": "litellm", "litellmKey": "gpt-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00003, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "OpenAI docs explicitly list this alias with gpt-4-0613." } }, { "id": "openai/gpt-4-0125-preview", "slug": "openai-gpt-4-0125-preview", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4-0125-preview", "displayName": "gpt-4-0125-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-03-26", "status": "retired", "announcementDate": "2025-09-26", "shutdownDate": "2026-03-26", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-4-0125-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-03-26", "input_cost_per_token": 0.00001, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4-turbo-preview" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "openai/gpt-4-0314", "slug": "openai-gpt-4-0314", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4-0314", "displayName": "gpt-4-0314", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-03-26", "status": "retired", "announcementDate": "2025-09-26", "shutdownDate": "2026-03-26", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-4-0314", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-03-26", "input_cost_per_token": 0.00003, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00006, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "openai/gpt-4-0613", "slug": "openai-gpt-4-0613", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4-0613", "displayName": "gpt-4-0613", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2025-06-06", "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-4-0613", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2025-06-06", "input_cost_per_token": 0.00003, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "openai/gpt-4-1106-preview", "slug": "openai-gpt-4-1106-preview", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4-1106-preview", "displayName": "gpt-4-1106-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-03-26", "status": "retired", "announcementDate": "2025-09-26", "shutdownDate": "2026-03-26", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-4-1106-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-03-26", "input_cost_per_token": 0.00001, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "openai/gpt-4-turbo", "slug": "openai-gpt-4-turbo", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4-turbo", "displayName": "gpt-4-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-4-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4-turbo" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "openai/gpt-4-turbo-2024-04-09", "slug": "openai-gpt-4-turbo-2024-04-09", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4-turbo-2024-04-09", "displayName": "gpt-4-turbo-2024-04-09", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "OpenAI docs explicitly list this snapshot under gpt-4-turbo." }, "source": { "type": "litellm", "litellmKey": "gpt-4-turbo-2024-04-09", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4-turbo" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "OpenAI docs explicitly list this snapshot under gpt-4-turbo." } }, { "id": "openai/gpt-4-turbo-preview", "slug": "openai-gpt-4-turbo-preview", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4-turbo-preview", "displayName": "gpt-4-turbo-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2025-09-26", "shutdownDate": "2026-03-26", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "OpenAI docs explicitly say this alias points to gpt-4-0125-preview." }, "source": { "type": "litellm", "litellmKey": "gpt-4-turbo-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4-turbo-preview" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "OpenAI docs explicitly say this alias points to gpt-4-0125-preview." } }, { "id": "openai/gpt-4.1", "slug": "openai-gpt-4-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4.1", "displayName": "GPT-4.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 4, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 14, "priorityCachedInputUsdPer1MTokens": 0.875, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004, "output_cost_per_token_priority": 0.000014 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004, "output_cost_per_token_priority": 0.000014, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4.1" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "openai/gpt-4.1-2025-04-14", "slug": "openai-gpt-4-1-2025-04-14", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4.1-2025-04-14", "displayName": "gpt-4.1-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 4, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4.1-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4.1" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "openai/gpt-4.1-mini", "slug": "openai-gpt-4-1-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4.1-mini", "displayName": "GPT-4.1 mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.19999999999999998, "batchOutputUsdPer1MTokens": 0.7999999999999999, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.7, "priorityOutputUsdPer1MTokens": 2.8, "priorityCachedInputUsdPer1MTokens": 0.175, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "cache_read_input_token_cost_priority": 1.75e-7, "input_cost_per_token": 4e-7, "input_cost_per_token_batches": 2e-7, "input_cost_per_token_priority": 7e-7, "output_cost_per_token": 0.0000016, "output_cost_per_token_batches": 8e-7, "output_cost_per_token_priority": 0.0000028 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4.1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1e-7, "cache_read_input_token_cost_priority": 1.75e-7, "input_cost_per_token": 4e-7, "input_cost_per_token_batches": 2e-7, "input_cost_per_token_priority": 7e-7, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000016, "output_cost_per_token_batches": 8e-7, "output_cost_per_token_priority": 0.0000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4.1-mini" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt41mini_officiallaunchpost_5": { "label": "SWE-bench Verified", "category": "coding", "score": 23.6, "scoreText": "23.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-mini", "exactModelOrSnapshot": "GPT-4.1 mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table for the GPT-4.1 family." }, "aider_polyglot": { "label": "Aider Polyglot", "category": "coding", "score": 58.2, "metric": "percent_correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-23" }, "livebench": { "label": "LiveBench", "category": "general", "score": null, "metric": "overall", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-23" } } }, { "id": "openai/gpt-4.1-mini-2025-04-14", "slug": "openai-gpt-4-1-mini-2025-04-14", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4.1-mini-2025-04-14", "displayName": "gpt-4.1-mini-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.19999999999999998, "batchOutputUsdPer1MTokens": 0.7999999999999999, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 4e-7, "input_cost_per_token_batches": 2e-7, "output_cost_per_token": 0.0000016, "output_cost_per_token_batches": 8e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4.1-mini-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 4e-7, "input_cost_per_token_batches": 2e-7, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000016, "output_cost_per_token_batches": 8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4.1-mini" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt41mini_officiallaunchpost_5": { "label": "SWE-bench Verified", "category": "coding", "score": 23.6, "scoreText": "23.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-mini", "exactModelOrSnapshot": "GPT-4.1 mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table for the GPT-4.1 family." } } }, { "id": "openai/gpt-4.1-nano", "slug": "openai-gpt-4-1-nano", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4.1-nano", "displayName": "gpt-4.1-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.049999999999999996, "batchOutputUsdPer1MTokens": 0.19999999999999998, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.19999999999999998, "priorityOutputUsdPer1MTokens": 0.7999999999999999, "priorityCachedInputUsdPer1MTokens": 0.049999999999999996, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token": 1e-7, "input_cost_per_token_batches": 5e-8, "input_cost_per_token_priority": 2e-7, "output_cost_per_token": 4e-7, "output_cost_per_token_batches": 2e-7, "output_cost_per_token_priority": 8e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-4.1-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token": 1e-7, "input_cost_per_token_batches": 5e-8, "input_cost_per_token_priority": 2e-7, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-7, "output_cost_per_token_batches": 2e-7, "output_cost_per_token_priority": 8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4.1-nano" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "aime24_accuracy_gpt41nano_officiallaunchpost_6": { "label": "AIME 2024", "category": "reasoning", "score": 29.4, "scoreText": "29.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-nano", "exactModelOrSnapshot": "GPT-4.1 nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Academic-knowledge appendix comparison row for the nano model." }, "mmlu_accuracy_gpt41nano_officiallaunchpost_258": { "label": "MMLU", "category": "general_knowledge", "score": 80.1, "scoreText": "80.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the narrative and table." }, "gpqa_accuracy_gpt41nano_officiallaunchpost_259": { "label": "GPQA", "category": "reasoning", "score": 50.3, "scoreText": "50.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." }, "aiderpolyglotcoding_passrate_gpt41nano_officiallaunchpost_260": { "label": "Aider Polyglot", "category": "coding", "score": 9.8, "scoreText": "9.8%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." } } }, { "id": "openai/gpt-4.1-nano-2025-04-14", "slug": "openai-gpt-4-1-nano-2025-04-14", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4.1-nano-2025-04-14", "displayName": "gpt-4.1-nano-2025-04-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.049999999999999996, "batchOutputUsdPer1MTokens": 0.19999999999999998, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, "input_cost_per_token_batches": 5e-8, "output_cost_per_token": 4e-7, "output_cost_per_token_batches": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "OpenAI docs explicitly list this snapshot under gpt-4.1-nano." }, "source": { "type": "litellm", "litellmKey": "gpt-4.1-nano-2025-04-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, "input_cost_per_token_batches": 5e-8, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-7, "output_cost_per_token_batches": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4.1-nano" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "OpenAI docs explicitly list this snapshot under gpt-4.1-nano." }, "benchmarks": { "aime24_accuracy_gpt41nano_officiallaunchpost_6": { "label": "AIME 2024", "category": "reasoning", "score": 29.4, "scoreText": "29.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-nano", "exactModelOrSnapshot": "GPT-4.1 nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Academic-knowledge appendix comparison row for the nano model." }, "mmlu_accuracy_gpt41nano_officiallaunchpost_258": { "label": "MMLU", "category": "general_knowledge", "score": 80.1, "scoreText": "80.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the narrative and table." }, "gpqa_accuracy_gpt41nano_officiallaunchpost_259": { "label": "GPQA", "category": "reasoning", "score": 50.3, "scoreText": "50.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." }, "aiderpolyglotcoding_passrate_gpt41nano_officiallaunchpost_260": { "label": "Aider Polyglot", "category": "coding", "score": 9.8, "scoreText": "9.8%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." } } }, { "id": "openai/gpt-4o", "slug": "openai-gpt-4o", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o", "displayName": "gpt-4o", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.25, "batchOutputUsdPer1MTokens": 5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 4.25, "priorityOutputUsdPer1MTokens": 17, "priorityCachedInputUsdPer1MTokens": 2.125, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "cache_read_input_token_cost_priority": 0.000002125, "input_cost_per_token": 0.0000025, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.00000425, "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_priority": 0.000017 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000125, "cache_read_input_token_cost_priority": 0.000002125, "input_cost_per_token": 0.0000025, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.00000425, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_priority": 0.000017, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4o" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-2024-05-13", "slug": "openai-gpt-4o-2024-05-13", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-2024-05-13", "displayName": "gpt-4o-2024-05-13", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 2.5, "batchOutputUsdPer1MTokens": 7.5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 8.75, "priorityOutputUsdPer1MTokens": 26.25, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.00000875, "output_cost_per_token": 0.000015, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00002625 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-2024-05-13", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000005, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.00000875, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00002625, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-2024-08-06", "slug": "openai-gpt-4o-2024-08-06", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-2024-08-06", "displayName": "gpt-4o-2024-08-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.25, "batchOutputUsdPer1MTokens": 5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "input_cost_per_token_batches": 0.00000125, "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-2024-08-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "input_cost_per_token_batches": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4o" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-2024-11-20", "slug": "openai-gpt-4o-2024-11-20", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-2024-11-20", "displayName": "gpt-4o-2024-11-20", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.25, "batchOutputUsdPer1MTokens": 5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "input_cost_per_token_batches": 0.00000125, "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-2024-11-20", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "input_cost_per_token_batches": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4o" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-audio-preview", "slug": "openai-gpt-4o-audio-preview", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-audio-preview", "displayName": "gpt-4o-audio-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-audio-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-audio-preview-2024-12-17", "slug": "openai-gpt-4o-audio-preview-2024-12-17", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-audio-preview-2024-12-17", "displayName": "gpt-4o-audio-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-audio-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-audio-preview-2025-06-03", "slug": "openai-gpt-4o-audio-preview-2025-06-03", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-audio-preview-2025-06-03", "displayName": "gpt-4o-audio-preview-2025-06-03", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-audio-preview-2025-06-03", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-audio", "slug": "openai-gpt-audio", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-audio", "displayName": "gpt-audio", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 32, "audioOutputUsdPer1MTokens": 64, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000032, "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-audio", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.000032, "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false } }, { "id": "openai/gpt-audio-1.5", "slug": "openai-gpt-audio-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-audio-1.5", "displayName": "gpt-audio-1.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 32, "audioOutputUsdPer1MTokens": 64, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000032, "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-audio-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.000032, "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false } }, { "id": "openai/gpt-audio-2025-08-28", "slug": "openai-gpt-audio-2025-08-28", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-audio-2025-08-28", "displayName": "gpt-audio-2025-08-28", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 32, "audioOutputUsdPer1MTokens": 64, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000032, "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-audio-2025-08-28", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.000032, "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false } }, { "id": "openai/gpt-audio-mini", "slug": "openai-gpt-audio-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-audio-mini", "displayName": "gpt-audio-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-audio-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false } }, { "id": "openai/gpt-audio-mini-2025-10-06", "slug": "openai-gpt-audio-mini-2025-10-06", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-audio-mini-2025-10-06", "displayName": "gpt-audio-mini-2025-10-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-07-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-audio-mini-2025-10-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "openai/gpt-audio-mini-2025-12-15", "slug": "openai-gpt-audio-mini-2025-12-15", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-audio-mini-2025-12-15", "displayName": "gpt-audio-mini-2025-12-15", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "prompt_caching": false, "reasoning": false, "response_schema": false, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-audio-mini-2025-12-15", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false } }, { "id": "openai/gpt-4o-mini", "slug": "openai-gpt-4o-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini", "displayName": "gpt-4o-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.075, "batchOutputUsdPer1MTokens": 0.3, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.25, "priorityOutputUsdPer1MTokens": 1, "priorityCachedInputUsdPer1MTokens": 0.125, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_priority": 1.25e-7, "input_cost_per_token": 1.5e-7, "input_cost_per_token_batches": 7.5e-8, "input_cost_per_token_priority": 2.5e-7, "output_cost_per_token": 6e-7, "output_cost_per_token_batches": 3e-7, "output_cost_per_token_priority": 0.000001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_priority": 1.25e-7, "input_cost_per_token": 1.5e-7, "input_cost_per_token_batches": 7.5e-8, "input_cost_per_token_priority": 2.5e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-7, "output_cost_per_token_batches": 3e-7, "output_cost_per_token_priority": 0.000001, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4o-mini" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-2024-07-18", "slug": "openai-gpt-4o-mini-2024-07-18", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-2024-07-18", "displayName": "gpt-4o-mini-2024-07-18", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.075, "batchOutputUsdPer1MTokens": 0.3, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, "input_cost_per_token_batches": 7.5e-8, "output_cost_per_token": 6e-7, "output_cost_per_token_batches": 3e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-2024-07-18", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, "input_cost_per_token_batches": 7.5e-8, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-7, "output_cost_per_token_batches": 3e-7, "search_context_cost_per_query": { "search_context_size_high": 0.03, "search_context_size_low": 0.025, "search_context_size_medium": 0.0275 }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-4o-mini" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-audio-preview", "slug": "openai-gpt-4o-mini-audio-preview", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-audio-preview", "displayName": "gpt-4o-mini-audio-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 1.5e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-audio-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 1.5e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 6e-7, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-audio-preview-2024-12-17", "slug": "openai-gpt-4o-mini-audio-preview-2024-12-17", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-audio-preview-2024-12-17", "displayName": "gpt-4o-mini-audio-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 1.5e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-audio-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 1.5e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 6e-7, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-realtime-preview", "slug": "openai-gpt-4o-mini-realtime-preview", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-realtime-preview", "displayName": "gpt-4o-mini-realtime-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-realtime-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-realtime-preview-2024-12-17", "slug": "openai-gpt-4o-mini-realtime-preview-2024-12-17", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-realtime-preview-2024-12-17", "displayName": "gpt-4o-mini-realtime-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-realtime-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-search-preview", "slug": "openai-gpt-4o-mini-search-preview", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-search-preview", "displayName": "gpt-4o-mini-search-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.075, "batchOutputUsdPer1MTokens": 0.3, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, "input_cost_per_token_batches": 7.5e-8, "output_cost_per_token": 6e-7, "output_cost_per_token_batches": 3e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-search-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, "input_cost_per_token_batches": 7.5e-8, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-7, "output_cost_per_token_batches": 3e-7, "search_context_cost_per_query": { "search_context_size_high": 0.03, "search_context_size_low": 0.025, "search_context_size_medium": 0.0275 }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-search-preview-2025-03-11", "slug": "openai-gpt-4o-mini-search-preview-2025-03-11", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-search-preview-2025-03-11", "displayName": "gpt-4o-mini-search-preview-2025-03-11", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.075, "batchOutputUsdPer1MTokens": 0.3, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, "input_cost_per_token_batches": 7.5e-8, "output_cost_per_token": 6e-7, "output_cost_per_token_batches": 3e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-07-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-search-preview-2025-03-11", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, "input_cost_per_token_batches": 7.5e-8, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-7, "output_cost_per_token_batches": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-transcribe", "slug": "openai-gpt-4o-mini-transcribe", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-transcribe", "displayName": "gpt-4o-mini-transcribe", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1.25, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": null, "maxInputTokens": 16000, "maxOutputTokens": 2000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-transcribe", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 0.000005, "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-tts", "slug": "openai-gpt-4o-mini-tts", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-tts", "displayName": "gpt-4o-mini-tts", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": 12, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.00025, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "audio" ] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-tts", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "mode": "audio_speech", "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ] }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-realtime-preview", "slug": "openai-gpt-4o-realtime-preview", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-realtime-preview", "displayName": "gpt-4o-realtime-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 20, "cachedInputUsdPer1MTokens": 2.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.000005, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-realtime-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.000005, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-realtime-preview-2024-12-17", "slug": "openai-gpt-4o-realtime-preview-2024-12-17", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-realtime-preview-2024-12-17", "displayName": "gpt-4o-realtime-preview-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 20, "cachedInputUsdPer1MTokens": 2.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.000005, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-realtime-preview-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.000005, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-realtime-preview-2025-06-03", "slug": "openai-gpt-4o-realtime-preview-2025-06-03", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-realtime-preview-2025-06-03", "displayName": "gpt-4o-realtime-preview-2025-06-03", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 20, "cachedInputUsdPer1MTokens": 2.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 40, "audioOutputUsdPer1MTokens": 80, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.000005, "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-realtime-preview-2025-06-03", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_audio_token": 0.00004, "input_cost_per_token": 0.000005, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-search-preview", "slug": "openai-gpt-4o-search-preview", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-search-preview", "displayName": "gpt-4o-search-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.25, "batchOutputUsdPer1MTokens": 5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "input_cost_per_token_batches": 0.00000125, "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-search-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "input_cost_per_token_batches": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005, "search_context_cost_per_query": { "search_context_size_high": 0.05, "search_context_size_low": 0.03, "search_context_size_medium": 0.035 }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-search-preview-2025-03-11", "slug": "openai-gpt-4o-search-preview-2025-03-11", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-search-preview-2025-03-11", "displayName": "gpt-4o-search-preview-2025-03-11", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.25, "batchOutputUsdPer1MTokens": 5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "input_cost_per_token_batches": 0.00000125, "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-07-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-search-preview-2025-03-11", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "input_cost_per_token_batches": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-4o-transcribe", "slug": "openai-gpt-4o-transcribe", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-transcribe", "displayName": "gpt-4o-transcribe", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 2.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.0000025, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": null, "maxInputTokens": 16000, "maxOutputTokens": 2000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-transcribe", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.0000025, "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openai/gpt-image-1.5", "slug": "openai-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00001, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.000032 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_token": 0.00001, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.000032, "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/gpt-image-1.5-2025-12-16", "slug": "openai-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00001, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.000032 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_token": 0.00001, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.000032, "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/gpt-image-2", "slug": "openai-gpt-image-2", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-2", "displayName": "gpt-image-2", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00001, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.00003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-image-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_token": 0.00001, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.00003, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/gpt-image-2-2026-04-21", "slug": "openai-gpt-image-2-2026-04-21", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-2-2026-04-21", "displayName": "gpt-image-2-2026-04-21", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00001, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.00003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-image-2-2026-04-21", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.000002, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_token": 0.00001, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.00003, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/low/1024-x-1024/gpt-image-1.5", "slug": "openai-low-1024-x-1024-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 9000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.009 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1024-x-1024/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/low/1024-x-1536/gpt-image-1.5", "slug": "openai-low-1024-x-1536-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1024-x-1536/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/low/1536-x-1024/gpt-image-1.5", "slug": "openai-low-1536-x-1024-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1536-x-1024/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/medium/1024-x-1024/gpt-image-1.5", "slug": "openai-medium-1024-x-1024-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 34000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.034 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1024-x-1024/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.034, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/medium/1024-x-1536/gpt-image-1.5", "slug": "openai-medium-1024-x-1536-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 50000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.05 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1024-x-1536/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/medium/1536-x-1024/gpt-image-1.5", "slug": "openai-medium-1536-x-1024-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 50000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.05 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1536-x-1024/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/high/1024-x-1024/gpt-image-1.5", "slug": "openai-high-1024-x-1024-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 133000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.133 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "high/1024-x-1024/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.133, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/high/1024-x-1536/gpt-image-1.5", "slug": "openai-high-1024-x-1536-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 200000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.2 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "high/1024-x-1536/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/high/1536-x-1024/gpt-image-1.5", "slug": "openai-high-1536-x-1024-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 200000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.2 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "high/1536-x-1024/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/standard/1024-x-1024/gpt-image-1.5", "slug": "openai-standard-1024-x-1024-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 9000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.009 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "standard/1024-x-1024/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/standard/1024-x-1536/gpt-image-1.5", "slug": "openai-standard-1024-x-1536-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "standard/1024-x-1536/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/standard/1536-x-1024/gpt-image-1.5", "slug": "openai-standard-1536-x-1024-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "standard/1536-x-1024/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/1024-x-1024/gpt-image-1.5", "slug": "openai-1024-x-1024-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 9000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.009 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "1024-x-1024/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/1024-x-1536/gpt-image-1.5", "slug": "openai-1024-x-1536-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "1024-x-1536/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/1536-x-1024/gpt-image-1.5", "slug": "openai-1536-x-1024-gpt-image-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5", "displayName": "gpt-image-1.5 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "1536-x-1024/gpt-image-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/low/1024-x-1024/gpt-image-1.5-2025-12-16", "slug": "openai-low-1024-x-1024-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 9000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.009 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1024-x-1024/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/low/1024-x-1536/gpt-image-1.5-2025-12-16", "slug": "openai-low-1024-x-1536-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1024-x-1536/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/low/1536-x-1024/gpt-image-1.5-2025-12-16", "slug": "openai-low-1536-x-1024-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1536-x-1024/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/medium/1024-x-1024/gpt-image-1.5-2025-12-16", "slug": "openai-medium-1024-x-1024-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 34000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.034 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1024-x-1024/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.034, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/medium/1024-x-1536/gpt-image-1.5-2025-12-16", "slug": "openai-medium-1024-x-1536-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 50000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.05 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1024-x-1536/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/medium/1536-x-1024/gpt-image-1.5-2025-12-16", "slug": "openai-medium-1536-x-1024-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 50000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.05 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1536-x-1024/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/high/1024-x-1024/gpt-image-1.5-2025-12-16", "slug": "openai-high-1024-x-1024-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 133000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.133 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "high/1024-x-1024/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.133, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/high/1024-x-1536/gpt-image-1.5-2025-12-16", "slug": "openai-high-1024-x-1536-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 200000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.2 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "high/1024-x-1536/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/high/1536-x-1024/gpt-image-1.5-2025-12-16", "slug": "openai-high-1536-x-1024-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 200000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.2 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "high/1536-x-1024/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/standard/1024-x-1024/gpt-image-1.5-2025-12-16", "slug": "openai-standard-1024-x-1024-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 9000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.009 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "standard/1024-x-1024/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/standard/1024-x-1536/gpt-image-1.5-2025-12-16", "slug": "openai-standard-1024-x-1536-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "standard/1024-x-1536/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/standard/1536-x-1024/gpt-image-1.5-2025-12-16", "slug": "openai-standard-1536-x-1024-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "standard/1536-x-1024/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/1024-x-1024/gpt-image-1.5-2025-12-16", "slug": "openai-1024-x-1024-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 9000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.009 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "1024-x-1024/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/1024-x-1536/gpt-image-1.5-2025-12-16", "slug": "openai-1024-x-1536-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "1024-x-1536/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/1536-x-1024/gpt-image-1.5-2025-12-16", "slug": "openai-1536-x-1024-gpt-image-1-5-2025-12-16", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1.5-2025-12-16", "displayName": "gpt-image-1.5-2025-12-16 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 13000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.013 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "1536-x-1024/gpt-image-1.5-2025-12-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true } }, { "id": "openai/gpt-5", "slug": "openai-gpt-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5", "displayName": "gpt-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.5, "priorityOutputUsdPer1MTokens": 20, "priorityCachedInputUsdPer1MTokens": 0.25, "flexInputUsdPer1MTokens": 0.625, "flexOutputUsdPer1MTokens": 5, "flexCachedInputUsdPer1MTokens": 0.0625, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openai/gpt-5.1", "slug": "openai-gpt-5-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.1", "displayName": "gpt-5.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.5, "priorityOutputUsdPer1MTokens": 20, "priorityCachedInputUsdPer1MTokens": 0.25, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.1" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "openai/gpt-5.1-2025-11-13", "slug": "openai-gpt-5-1-2025-11-13", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.1-2025-11-13", "displayName": "gpt-5.1-2025-11-13", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.5, "priorityOutputUsdPer1MTokens": 20, "priorityCachedInputUsdPer1MTokens": 0.25, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.1-2025-11-13", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.1" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "openai/gpt-5.1-chat-latest", "slug": "openai-gpt-5-1-chat-latest", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.1-chat-latest", "displayName": "gpt-5.1-chat-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.5, "priorityOutputUsdPer1MTokens": 20, "priorityCachedInputUsdPer1MTokens": 0.25, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": false, "native_streaming": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": false, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-07-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.1-chat-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "openai/gpt-5.2", "slug": "openai-gpt-5-2", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.2", "displayName": "gpt-5.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 28, "priorityCachedInputUsdPer1MTokens": 0.35, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.2" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "openai/gpt-5.2-2025-12-11", "slug": "openai-gpt-5-2-2025-12-11", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.2-2025-12-11", "displayName": "gpt-5.2-2025-12-11", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 28, "priorityCachedInputUsdPer1MTokens": 0.35, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.2-2025-12-11", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.2" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "openai/gpt-5.2-chat-latest", "slug": "openai-gpt-5-2-chat-latest", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.2-chat-latest", "displayName": "gpt-5.2-chat-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 28, "priorityCachedInputUsdPer1MTokens": 0.35, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-05-08", "shutdownDate": "2026-08-10", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.2-chat-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "openai/gpt-5.3-chat-latest", "slug": "openai-gpt-5-3-chat-latest", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.3-chat-latest", "displayName": "gpt-5.3-chat-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 28, "priorityCachedInputUsdPer1MTokens": 0.35, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-05-08", "shutdownDate": "2026-08-10", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.3-chat-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "openai/gpt-5.2-pro", "slug": "openai-gpt-5-2-pro", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.2-pro", "displayName": "gpt-5.2-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 21, "outputUsdPer1MTokens": 168, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.2-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000021, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.2-pro" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" } }, { "id": "openai/gpt-5.2-pro-2025-12-11", "slug": "openai-gpt-5-2-pro-2025-12-11", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.2-pro-2025-12-11", "displayName": "gpt-5.2-pro-2025-12-11", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 21, "outputUsdPer1MTokens": 168, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.2-pro-2025-12-11", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000021, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.2-pro" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" } }, { "id": "openai/gpt-5.5", "slug": "openai-gpt-5-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.5", "displayName": "gpt-5.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 2.5, "batchOutputUsdPer1MTokens": 15, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 10, "priorityOutputUsdPer1MTokens": 60, "priorityCachedInputUsdPer1MTokens": 1, "flexInputUsdPer1MTokens": 2.5, "flexOutputUsdPer1MTokens": 15, "flexCachedInputUsdPer1MTokens": 0.25, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 10, "above272kOutputUsdPer1MTokens": 45, "above272kCachedInputUsdPer1MTokens": 1, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.000001, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.00001, "output_cost_per_token": 0.00003, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_priority": 0.00006 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.000001, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.00001, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00003, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_priority": 0.00006, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.5" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "livebench_livebenchscore_gpt55thinkingxhigheffort_benchmarkleaderboard_227": { "label": "LiveBench", "category": "general_knowledge", "score": 80.71, "scoreText": "80.71", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt55high_benchmarkleaderboard_242": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1487, "scoreText": "1487±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "gpt-5.5-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." }, "gpqadiamond_accuracy_gpt55xhigh_benchmarkleaderboard_246": { "label": "GPQA Diamond", "category": "science", "score": 93.5, "scoreText": "93.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 (xhigh)", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis GPQA Diamond leaderboard row for the xhigh reasoning variant." }, "gpqadiamond_accuracy_gpt55high_benchmarkleaderboard_247": { "label": "GPQA Diamond", "category": "science", "score": 93.2, "scoreText": "93.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 (high)", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis GPQA Diamond leaderboard row for the high reasoning variant." } } }, { "id": "openai/gpt-5.5-2026-04-23", "slug": "openai-gpt-5-5-2026-04-23", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.5-2026-04-23", "displayName": "gpt-5.5-2026-04-23", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 2.5, "batchOutputUsdPer1MTokens": 15, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 10, "priorityOutputUsdPer1MTokens": 60, "priorityCachedInputUsdPer1MTokens": 1, "flexInputUsdPer1MTokens": 2.5, "flexOutputUsdPer1MTokens": 15, "flexCachedInputUsdPer1MTokens": 0.25, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 10, "above272kOutputUsdPer1MTokens": 45, "above272kCachedInputUsdPer1MTokens": 1, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.000001, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.00001, "output_cost_per_token": 0.00003, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_priority": 0.00006 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.5-2026-04-23", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.000001, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.00001, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00003, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_priority": 0.00006, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.5" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "livebench_livebenchscore_gpt55thinkingxhigheffort_benchmarkleaderboard_227": { "label": "LiveBench", "category": "general_knowledge", "score": 80.71, "scoreText": "80.71", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt55high_benchmarkleaderboard_242": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1487, "scoreText": "1487±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "gpt-5.5-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." }, "gpqadiamond_accuracy_gpt55xhigh_benchmarkleaderboard_246": { "label": "GPQA Diamond", "category": "science", "score": 93.5, "scoreText": "93.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 (xhigh)", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis GPQA Diamond leaderboard row for the xhigh reasoning variant." }, "gpqadiamond_accuracy_gpt55high_benchmarkleaderboard_247": { "label": "GPQA Diamond", "category": "science", "score": 93.2, "scoreText": "93.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.5", "exactModelOrSnapshot": "GPT-5.5 (high)", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis GPQA Diamond leaderboard row for the high reasoning variant." } } }, { "id": "openai/gpt-5.5-pro", "slug": "openai-gpt-5-5-pro", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.5-pro", "displayName": "gpt-5.5-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 180, "cachedInputUsdPer1MTokens": 3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 15, "batchOutputUsdPer1MTokens": 90, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": 15, "flexOutputUsdPer1MTokens": 90, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 60, "above272kOutputUsdPer1MTokens": 270, "above272kCachedInputUsdPer1MTokens": 6, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false, "low_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.5-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.5-pro" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" } }, { "id": "openai/gpt-5.5-pro-2026-04-23", "slug": "openai-gpt-5-5-pro-2026-04-23", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.5-pro-2026-04-23", "displayName": "gpt-5.5-pro-2026-04-23", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 180, "cachedInputUsdPer1MTokens": 3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 15, "batchOutputUsdPer1MTokens": 90, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": 15, "flexOutputUsdPer1MTokens": 90, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 60, "above272kOutputUsdPer1MTokens": 270, "above272kCachedInputUsdPer1MTokens": 6, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false, "low_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.5-pro-2026-04-23", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.5-pro" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" } }, { "id": "openai/gpt-5.4", "slug": "openai-gpt-5-4", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.4", "displayName": "gpt-5.4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.25, "batchOutputUsdPer1MTokens": 7.5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 5, "priorityOutputUsdPer1MTokens": 30, "priorityCachedInputUsdPer1MTokens": 0.5, "flexInputUsdPer1MTokens": 1.25, "flexOutputUsdPer1MTokens": 7.5, "flexCachedInputUsdPer1MTokens": 0.13, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 5, "above272kOutputUsdPer1MTokens": 22.5, "above272kCachedInputUsdPer1MTokens": 0.5, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_flex": 1.3e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_flex": 0.00000125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.000005, "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_flex": 0.0000075, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00003 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.4", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_flex": 1.3e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_flex": 0.00000125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.000005, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_flex": 0.0000075, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00003, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.4" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "livebench_livebenchscore_gpt54thinkingxhigheffort_benchmarkleaderboard_228": { "label": "LiveBench", "category": "general_knowledge", "score": 80.28, "scoreText": "80.28", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "GPT-5.4 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt54high_benchmarkleaderboard_244": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1483, "scoreText": "1483±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "gpt-5.4-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." } } }, { "id": "openai/gpt-5.4-2026-03-05", "slug": "openai-gpt-5-4-2026-03-05", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.4-2026-03-05", "displayName": "gpt-5.4-2026-03-05", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.25, "batchOutputUsdPer1MTokens": 7.5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 5, "priorityOutputUsdPer1MTokens": 30, "priorityCachedInputUsdPer1MTokens": 0.5, "flexInputUsdPer1MTokens": 1.25, "flexOutputUsdPer1MTokens": 7.5, "flexCachedInputUsdPer1MTokens": 0.13, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 5, "above272kOutputUsdPer1MTokens": 22.5, "above272kCachedInputUsdPer1MTokens": 0.5, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_flex": 1.3e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_flex": 0.00000125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.000005, "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_flex": 0.0000075, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00003 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.4-2026-03-05", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_flex": 1.3e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_flex": 0.00000125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.000005, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_flex": 0.0000075, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00003, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.4" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "livebench_livebenchscore_gpt54thinkingxhigheffort_benchmarkleaderboard_228": { "label": "LiveBench", "category": "general_knowledge", "score": 80.28, "scoreText": "80.28", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "GPT-5.4 Thinking xHigh Effort", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; page is JS-rendered, values taken from the current crawl snippet." }, "lmarenatextarenaenglish_arenaelo_gpt54high_benchmarkleaderboard_244": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1483, "scoreText": "1483±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5.4", "exactModelOrSnapshot": "gpt-5.4-high", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the high variant." } } }, { "id": "openai/gpt-5.4-pro", "slug": "openai-gpt-5-4-pro", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.4-pro", "displayName": "gpt-5.4-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 180, "cachedInputUsdPer1MTokens": 3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 15, "batchOutputUsdPer1MTokens": 90, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": 15, "flexOutputUsdPer1MTokens": 90, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 60, "above272kOutputUsdPer1MTokens": 270, "above272kCachedInputUsdPer1MTokens": 6, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.4-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.4-pro" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" } }, { "id": "openai/gpt-5.4-pro-2026-03-05", "slug": "openai-gpt-5-4-pro-2026-03-05", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.4-pro-2026-03-05", "displayName": "gpt-5.4-pro-2026-03-05", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 180, "cachedInputUsdPer1MTokens": 3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 15, "batchOutputUsdPer1MTokens": 90, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": 15, "flexOutputUsdPer1MTokens": 90, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": 60, "above272kOutputUsdPer1MTokens": 270, "above272kCachedInputUsdPer1MTokens": 6, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1050000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.4-pro-2026-03-05", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.000003, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token": 0.00003, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.4-pro" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" } }, { "id": "openai/gpt-5.4-mini", "slug": "openai-gpt-5-4-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.4-mini", "displayName": "gpt-5.4-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.75, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.375, "batchOutputUsdPer1MTokens": 2.25, "batchCachedInputUsdPer1MTokens": 0.0375, "priorityInputUsdPer1MTokens": 1.5, "priorityOutputUsdPer1MTokens": 9, "priorityCachedInputUsdPer1MTokens": 0.15, "flexInputUsdPer1MTokens": 0.375, "flexOutputUsdPer1MTokens": 2.25, "flexCachedInputUsdPer1MTokens": 0.0375, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token": 7.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "output_cost_per_token": 0.0000045, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.4-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token": 7.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000045, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.4-mini" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" } }, { "id": "openai/gpt-5.4-mini-2026-03-17", "slug": "openai-gpt-5-4-mini-2026-03-17", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.4-mini-2026-03-17", "displayName": "gpt-5.4-mini-2026-03-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.75, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.375, "batchOutputUsdPer1MTokens": 2.25, "batchCachedInputUsdPer1MTokens": 0.0375, "priorityInputUsdPer1MTokens": 1.5, "priorityOutputUsdPer1MTokens": 9, "priorityCachedInputUsdPer1MTokens": 0.15, "flexInputUsdPer1MTokens": 0.375, "flexOutputUsdPer1MTokens": 2.25, "flexCachedInputUsdPer1MTokens": 0.0375, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token": 7.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "output_cost_per_token": 0.0000045, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.4-mini-2026-03-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token": 7.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000045, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.4-mini" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" } }, { "id": "openai/gpt-5.4-nano", "slug": "openai-gpt-5-4-nano", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.4-nano", "displayName": "gpt-5.4-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.09999999999999999, "batchOutputUsdPer1MTokens": 0.625, "batchCachedInputUsdPer1MTokens": 0.01, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": 0.09999999999999999, "flexOutputUsdPer1MTokens": 0.625, "flexCachedInputUsdPer1MTokens": 0.01, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-8, "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_batches": 1e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "output_cost_per_token": 0.00000125, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.4-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2e-8, "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_batches": 1e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000125, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.4-nano" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" } }, { "id": "openai/gpt-5.4-nano-2026-03-17", "slug": "openai-gpt-5-4-nano-2026-03-17", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.4-nano-2026-03-17", "displayName": "gpt-5.4-nano-2026-03-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.09999999999999999, "batchOutputUsdPer1MTokens": 0.625, "batchCachedInputUsdPer1MTokens": 0.01, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": 0.09999999999999999, "flexOutputUsdPer1MTokens": 0.625, "flexCachedInputUsdPer1MTokens": 0.01, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-8, "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_batches": 1e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "output_cost_per_token": 0.00000125, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": true, "minimal": false, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": true, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.4-nano-2026-03-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2e-8, "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_batches": 1e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000125, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.4-nano" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" } }, { "id": "openai/gpt-5-pro", "slug": "openai-gpt-5-pro", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-pro", "displayName": "gpt-5-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 120, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 7.5, "batchOutputUsdPer1MTokens": 60, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "input_cost_per_token_batches": 0.0000075, "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 0.00006 } }, "limits": { "contextWindow": 272000, "maxInputTokens": 128000, "maxOutputTokens": 272000, "maxTokens": 272000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": false, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "input_cost_per_token_batches": 0.0000075, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 272000, "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 0.00006, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5-pro" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openai/gpt-5-pro-2025-10-06", "slug": "openai-gpt-5-pro-2025-10-06", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-pro-2025-10-06", "displayName": "gpt-5-pro-2025-10-06", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 120, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 7.5, "batchOutputUsdPer1MTokens": 60, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "input_cost_per_token_batches": 0.0000075, "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 0.00006 } }, "limits": { "contextWindow": 272000, "maxInputTokens": 128000, "maxOutputTokens": 272000, "maxTokens": 272000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": false, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-pro-2025-10-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "input_cost_per_token_batches": 0.0000075, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 272000, "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 0.00006, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5-pro" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openai/gpt-5-2025-08-07", "slug": "openai-gpt-5-2025-08-07", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-2025-08-07", "displayName": "gpt-5-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.5, "priorityOutputUsdPer1MTokens": 20, "priorityCachedInputUsdPer1MTokens": 0.25, "flexInputUsdPer1MTokens": 0.625, "flexOutputUsdPer1MTokens": 5, "flexCachedInputUsdPer1MTokens": 0.0625, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openai/gpt-5-chat", "slug": "openai-gpt-5-chat", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-chat", "displayName": "gpt-5-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": false, "native_streaming": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": false, "vision": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_vision": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openai/gpt-5-chat-latest", "slug": "openai-gpt-5-chat-latest", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-chat-latest", "displayName": "gpt-5-chat-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": false, "native_streaming": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": false, "vision": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-07-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-chat-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_vision": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5-chat-latest" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openai/gpt-5-codex", "slug": "openai-gpt-5-codex", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-codex", "displayName": "gpt-5-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-07-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openai/gpt-5.1-codex", "slug": "openai-gpt-5-1-codex", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.1-codex", "displayName": "gpt-5.1-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.5, "priorityOutputUsdPer1MTokens": 20, "priorityCachedInputUsdPer1MTokens": 0.25, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-07-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.1-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.1-codex" ], "manual_model_modalities_note": "OpenAI exact codex-model override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "openai/gpt-5.1-codex-max", "slug": "openai-gpt-5-1-codex-max", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.1-codex-max", "displayName": "gpt-5.1-codex-max", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-07-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.1-codex-max", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max" ], "manual_model_modalities_note": "OpenAI exact codex-model override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "openai/gpt-5.1-codex-mini", "slug": "openai-gpt-5-1-codex-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.1-codex-mini", "displayName": "gpt-5.1-codex-mini", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.44999999999999996, "priorityOutputUsdPer1MTokens": 3.5999999999999996, "priorityCachedInputUsdPer1MTokens": 0.045, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token": 2.5e-7, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_token": 0.000002, "output_cost_per_token_priority": 0.0000036 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-07-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.1-codex-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token": 2.5e-7, "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000002, "output_cost_per_token_priority": 0.0000036, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini" ], "manual_model_modalities_note": "OpenAI exact codex-model override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "openai/gpt-5.2-codex", "slug": "openai-gpt-5-2-codex", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.2-codex", "displayName": "gpt-5.2-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 28, "priorityCachedInputUsdPer1MTokens": 0.35, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": true }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-07-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.2-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.2-codex" ], "manual_model_modalities_note": "OpenAI exact codex-model override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "openai/gpt-5.3-codex", "slug": "openai-gpt-5-3-codex", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5.3-codex", "displayName": "gpt-5.3-codex", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 28, "priorityCachedInputUsdPer1MTokens": 0.35, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": false, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5.3-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000014, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5.3-codex" ], "manual_model_modalities_note": "OpenAI exact codex-model override from official model page" } }, { "id": "openai/gpt-5-mini", "slug": "openai-gpt-5-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-mini", "displayName": "gpt-5-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.44999999999999996, "priorityOutputUsdPer1MTokens": 3.5999999999999996, "priorityCachedInputUsdPer1MTokens": 0.045, "flexInputUsdPer1MTokens": 0.125, "flexOutputUsdPer1MTokens": 1, "flexCachedInputUsdPer1MTokens": 0.012499999999999999, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token": 2.5e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_token": 0.000002, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token": 2.5e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000002, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5-mini" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "openai/gpt-5-mini-2025-08-07", "slug": "openai-gpt-5-mini-2025-08-07", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-mini-2025-08-07", "displayName": "gpt-5-mini-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 0.44999999999999996, "priorityOutputUsdPer1MTokens": 3.5999999999999996, "priorityCachedInputUsdPer1MTokens": 0.045, "flexInputUsdPer1MTokens": 0.125, "flexOutputUsdPer1MTokens": 1, "flexCachedInputUsdPer1MTokens": 0.012499999999999999, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token": 2.5e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_token": 0.000002, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-mini-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token": 2.5e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000002, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5-mini" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "openai/gpt-5-nano", "slug": "openai-gpt-5-nano", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-nano", "displayName": "gpt-5-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.005, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2.5, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": 0.024999999999999998, "flexOutputUsdPer1MTokens": 0.19999999999999998, "flexCachedInputUsdPer1MTokens": 0.0025, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-9, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token": 5e-8, "input_cost_per_token_flex": 2.5e-8, "input_cost_per_token_priority": 0.0000025, "output_cost_per_token": 4e-7, "output_cost_per_token_flex": 2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-9, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token": 5e-8, "input_cost_per_token_flex": 2.5e-8, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-7, "output_cost_per_token_flex": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5-nano" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "aime2025_accuracy_gpt5nanohigh_officiallaunchpost_28": { "label": "AIME 2025", "category": "reasoning", "score": 85.2, "scoreText": "85.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-nano", "exactModelOrSnapshot": "GPT-5 nano (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." } } }, { "id": "openai/gpt-5-nano-2025-08-07", "slug": "openai-gpt-5-nano-2025-08-07", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-nano-2025-08-07", "displayName": "gpt-5-nano-2025-08-07", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.005, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": 0.024999999999999998, "flexOutputUsdPer1MTokens": 0.19999999999999998, "flexCachedInputUsdPer1MTokens": 0.0025, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-9, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token": 5e-8, "input_cost_per_token_flex": 2.5e-8, "output_cost_per_token": 4e-7, "output_cost_per_token_flex": 2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-nano-2025-08-07", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-9, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token": 5e-8, "input_cost_per_token_flex": 2.5e-8, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-7, "output_cost_per_token_flex": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/gpt-5-nano" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "aime2025_accuracy_gpt5nanohigh_officiallaunchpost_28": { "label": "AIME 2025", "category": "reasoning", "score": 85.2, "scoreText": "85.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-nano", "exactModelOrSnapshot": "GPT-5 nano (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." } } }, { "id": "openai/gpt-image-1", "slug": "openai-gpt-image-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1", "displayName": "gpt-image-1", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.0000025, "cache_read_input_token_cost": 0.00000125, "input_cost_per_image_token": 0.00001, "input_cost_per_token": 0.000005, "output_cost_per_image_token": 0.00004 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.0000025, "cache_read_input_token_cost": 0.00000125, "input_cost_per_image_token": 0.00001, "input_cost_per_token": 0.000005, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 0.00004, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "openai/gpt-image-1-mini", "slug": "openai-gpt-image-1-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 2.5e-7, "cache_read_input_token_cost": 2e-7, "input_cost_per_image_token": 0.0000025, "input_cost_per_token": 0.000002, "output_cost_per_image_token": 0.000008 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 2.5e-7, "cache_read_input_token_cost": 2e-7, "input_cost_per_image_token": 0.0000025, "input_cost_per_token": 0.000002, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 0.000008, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "id": "openai/gpt-realtime", "slug": "openai-gpt-realtime", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-realtime", "displayName": "gpt-realtime", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 4, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": 0.39999999999999997, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 32, "audioOutputUsdPer1MTokens": 64, "imageInputUsdPer1MUnits": 5, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 4e-7, "cache_read_input_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-realtime", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 4e-7, "cache_read_input_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/gpt-realtime-1.5", "slug": "openai-gpt-realtime-1-5", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-realtime-1.5", "displayName": "gpt-realtime-1.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 4, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": 0.39999999999999997, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 32, "audioOutputUsdPer1MTokens": 64, "imageInputUsdPer1MUnits": 5, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 4e-7, "cache_read_input_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-realtime-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 4e-7, "cache_read_input_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/gpt-realtime-2", "slug": "openai-gpt-realtime-2", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-realtime-2", "displayName": "gpt-realtime-2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 4, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": 0.39999999999999997, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 32, "audioOutputUsdPer1MTokens": 64, "imageInputUsdPer1MUnits": 5, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 4e-7, "cache_read_input_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-realtime-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 4e-7, "cache_read_input_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/gpt-realtime-mini", "slug": "openai-gpt-realtime-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-realtime-mini", "displayName": "gpt-realtime-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-realtime-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_token": 6e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/gpt-realtime-2025-08-28", "slug": "openai-gpt-realtime-2025-08-28", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-realtime-2025-08-28", "displayName": "gpt-realtime-2025-08-28", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 4, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": 0.39999999999999997, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 32, "audioOutputUsdPer1MTokens": 64, "imageInputUsdPer1MUnits": 5, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 4e-7, "cache_read_input_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-realtime-2025-08-28", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 4e-7, "cache_read_input_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000004, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.000016, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "gradient_ai/gradient_ai/alibaba-qwen3-32b", "slug": "gradient_ai-gradient_ai-alibaba-qwen3-32b", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "alibaba-qwen3-32b", "displayName": "alibaba-qwen3-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 40960, "maxInputTokens": 131072, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/alibaba-qwen3-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "gradient_ai", "max_tokens": 40960, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 131072, "max_output_tokens": 40960 } }, { "id": "gradient_ai/gradient_ai/anthropic-claude-3-opus", "slug": "gradient_ai-gradient_ai-anthropic-claude-3-opus", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "anthropic-claude-3-opus", "displayName": "anthropic-claude-3-opus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 200000, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/anthropic-claude-3-opus", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "litellm_provider": "gradient_ai", "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 0.000075, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 1024 }, "benchmarks": { "aiderrefactoringleaderboard_score_claude3opus20240229_benchmarkleaderboard_69": { "label": "Aider Refactoring", "category": "coding", "score": 72.3, "scoreText": "72.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/refactor.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3 Opus", "exactModelOrSnapshot": "claude-3-opus-20240229", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Refactoring leaderboard row; diff edit format." } } }, { "id": "gradient_ai/gradient_ai/anthropic-claude-3.5-haiku", "slug": "gradient_ai-gradient_ai-anthropic-claude-3-5-haiku", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "anthropic-claude-3.5-haiku", "displayName": "anthropic-claude-3.5-haiku", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 200000, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/anthropic-claude-3.5-haiku", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "gradient_ai", "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 0.000004, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 1024 }, "benchmarks": { "aidercodeeditingleaderboard_score_claude35haiku20241022_benchmarkleaderboard_68": { "label": "Aider Code Editing", "category": "coding", "score": 75.2, "scoreText": "75.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Haiku", "exactModelOrSnapshot": "claude-3-5-haiku-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." } } }, { "id": "gradient_ai/gradient_ai/anthropic-claude-3.5-sonnet", "slug": "gradient_ai-gradient_ai-anthropic-claude-3-5-sonnet", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "anthropic-claude-3.5-sonnet", "displayName": "anthropic-claude-3.5-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 200000, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/anthropic-claude-3.5-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "gradient_ai", "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 0.000015, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 1024 }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "gradient_ai/gradient_ai/anthropic-claude-3.7-sonnet", "slug": "gradient_ai-gradient_ai-anthropic-claude-3-7-sonnet", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "anthropic-claude-3.7-sonnet", "displayName": "anthropic-claude-3.7-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 200000, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/anthropic-claude-3.7-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "gradient_ai", "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 0.000015, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 1024 }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "gradient_ai/gradient_ai/deepseek-r1-distill-llama-70b", "slug": "gradient_ai-gradient_ai-deepseek-r1-distill-llama-70b", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "deepseek-r1-distill-llama-70b", "displayName": "deepseek-r1-distill-llama-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.9900000000000001, "outputUsdPer1MTokens": 0.9900000000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.9900000000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9.9e-7, "output_cost_per_token": 9.9e-7 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 32768, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/deepseek-r1-distill-llama-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9.9e-7, "litellm_provider": "gradient_ai", "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 9.9e-7, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 32768, "max_output_tokens": 8000 }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "gradient_ai/gradient_ai/llama3-8b-instruct", "slug": "gradient_ai-gradient_ai-llama3-8b-instruct", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "llama3-8b-instruct", "displayName": "llama3-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 512, "maxInputTokens": 8192, "maxOutputTokens": 512, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/llama3-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "gradient_ai", "max_tokens": 512, "mode": "chat", "output_cost_per_token": 2e-7, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 8192, "max_output_tokens": 512 } }, { "id": "gradient_ai/gradient_ai/llama3.3-70b-instruct", "slug": "gradient_ai-gradient_ai-llama3-3-70b-instruct", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "llama3.3-70b-instruct", "displayName": "llama3.3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.65, "outputUsdPer1MTokens": 0.65, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 6.5e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/llama3.3-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6.5e-7, "litellm_provider": "gradient_ai", "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 6.5e-7, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 128000, "max_output_tokens": 2048 }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "gradient_ai/gradient_ai/mistral-nemo-instruct-2407", "slug": "gradient_ai-gradient_ai-mistral-nemo-instruct-2407", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "mistral-nemo-instruct-2407", "displayName": "mistral-nemo-instruct-2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 512, "maxInputTokens": 128000, "maxOutputTokens": 512, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/mistral-nemo-instruct-2407", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "gradient_ai", "max_tokens": 512, "mode": "chat", "output_cost_per_token": 3e-7, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 128000, "max_output_tokens": 512 }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "gradient_ai/gradient_ai/openai-gpt-4o", "slug": "gradient_ai-gradient_ai-openai-gpt-4o", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "openai-gpt-4o", "displayName": "openai-gpt-4o", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/openai-gpt-4o", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "gradient_ai", "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 128000, "max_output_tokens": 16384 }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "gradient_ai/gradient_ai/openai-gpt-4o-mini", "slug": "gradient_ai-gradient_ai-openai-gpt-4o-mini", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "openai-gpt-4o-mini", "displayName": "openai-gpt-4o-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/openai-gpt-4o-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "gradient_ai", "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 128000, "max_output_tokens": 16384 }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "gradient_ai/gradient_ai/openai-o3", "slug": "gradient_ai-gradient_ai-openai-o3", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "openai-o3", "displayName": "openai-o3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/openai-o3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "gradient_ai", "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000008, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 100000 } }, { "id": "gradient_ai/gradient_ai/openai-o3-mini", "slug": "gradient_ai-gradient_ai-openai-o3-mini", "provider": "gradient_ai", "providerSlug": "gradient_ai", "name": "openai-o3-mini", "displayName": "openai-o3-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [], "output": [] }, "endpoints": [ "/v1/chat/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gradient_ai/openai-o3-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000011, "litellm_provider": "gradient_ai", "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 100000 }, "benchmarks": { "aime2024_accuracy_o3minihigh_officiallaunchpost_18": { "label": "AIME 2024", "category": "reasoning", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "gpqadiamond_accuracy_o3minihigh_officiallaunchpost_19": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 77, "scoreText": "77.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "swebenchverified_accuracy_o3minihigh_officiallaunchpost_20": { "label": "SWE-bench Verified", "category": "coding", "score": 48.9, "scoreText": "48.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; n=477 verified tasks." } } }, { "id": "lemonade/lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF", "slug": "lemonade-lemonade-qwen3-coder-30b-a3b-instruct-gguf", "provider": "lemonade", "providerSlug": "lemonade", "name": "Qwen3-Coder-30B-A3B-Instruct-GGUF", "displayName": "Qwen3-Coder-30B-A3B-Instruct-GGUF", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 262144, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_tokens": 32768, "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "lemonade/lemonade/gpt-oss-20b-mxfp4-GGUF", "slug": "lemonade-lemonade-gpt-oss-20b-mxfp4-gguf", "provider": "lemonade", "providerSlug": "lemonade", "name": "gpt-oss-20b-mxfp4-GGUF", "displayName": "gpt-oss-20b-mxfp4-GGUF", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lemonade/gpt-oss-20b-mxfp4-GGUF", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_tokens": 32768, "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "lemonade/lemonade/gpt-oss-120b-mxfp-GGUF", "slug": "lemonade-lemonade-gpt-oss-120b-mxfp-gguf", "provider": "lemonade", "providerSlug": "lemonade", "name": "gpt-oss-120b-mxfp-GGUF", "displayName": "gpt-oss-120b-mxfp-GGUF", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lemonade/gpt-oss-120b-mxfp-GGUF", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_tokens": 32768, "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "lemonade/lemonade/Gemma-3-4b-it-GGUF", "slug": "lemonade-lemonade-gemma-3-4b-it-gguf", "provider": "lemonade", "providerSlug": "lemonade", "name": "Gemma-3-4b-it-GGUF", "displayName": "Gemma-3-4b-it-GGUF", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lemonade/Gemma-3-4b-it-GGUF", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "lemonade/lemonade/Qwen3-4B-Instruct-2507-GGUF", "slug": "lemonade-lemonade-qwen3-4b-instruct-2507-gguf", "provider": "lemonade", "providerSlug": "lemonade", "name": "Qwen3-4B-Instruct-2507-GGUF", "displayName": "Qwen3-4B-Instruct-2507-GGUF", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 262144, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lemonade/Qwen3-4B-Instruct-2507-GGUF", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_tokens": 32768, "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true } }, { "id": "amazon_nova/amazon-nova/nova-micro-v1", "slug": "amazon_nova-amazon-nova-nova-micro-v1", "provider": "amazon_nova", "providerSlug": "amazon_nova", "name": "nova-micro-v1", "displayName": "nova-micro-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.035, "outputUsdPer1MTokens": 0.14, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.035, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.4e-7 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 128000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon-nova/nova-micro-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.5e-8, "litellm_provider": "amazon_nova", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-7, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true } }, { "id": "amazon_nova/amazon-nova/nova-lite-v1", "slug": "amazon_nova-amazon-nova-nova-lite-v1", "provider": "amazon_nova", "providerSlug": "amazon_nova", "name": "nova-lite-v1", "displayName": "nova-lite-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon-nova/nova-lite-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-7, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true } }, { "id": "amazon_nova/amazon-nova/nova-premier-v1", "slug": "amazon_nova-amazon-nova-nova-premier-v1", "provider": "amazon_nova", "providerSlug": "amazon_nova", "name": "nova-premier-v1", "displayName": "nova-premier-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 12.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.0000125 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 1000000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": false, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon-nova/nova-premier-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "amazon_nova", "max_input_tokens": 1000000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 0.0000125, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_response_schema": true, "supports_vision": true } }, { "id": "amazon_nova/amazon-nova/nova-pro-v1", "slug": "amazon_nova-amazon-nova-nova-pro-v1", "provider": "amazon_nova", "providerSlug": "amazon_nova", "name": "nova-pro-v1", "displayName": "nova-pro-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 3.1999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000032 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "amazon-nova/nova-pro-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 0.0000032, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true } }, { "id": "groq/groq/llama-3.1-8b-instant", "slug": "groq-groq-llama-3-1-8b-instant", "provider": "Groq", "providerSlug": "groq", "name": "llama-3.1-8b-instant", "displayName": "llama-3.1-8b-instant", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/llama-3.1-8b-instant", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "groq", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-8, "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "groq/groq/llama-3.3-70b-versatile", "slug": "groq-groq-llama-3-3-70b-versatile", "provider": "Groq", "providerSlug": "groq", "name": "llama-3.3-70b-versatile", "displayName": "llama-3.3-70b-versatile", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.59, "outputUsdPer1MTokens": 0.7899999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.59, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.9e-7, "output_cost_per_token": 7.9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 128000, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/llama-3.3-70b-versatile", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5.9e-7, "litellm_provider": "groq", "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.9e-7, "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "groq/groq/gemma-7b-it", "slug": "groq-groq-gemma-7b-it", "provider": "Groq", "providerSlug": "groq", "name": "gemma-7b-it", "displayName": "gemma-7b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2024-12-11", "shutdownDate": "2024-12-18", "earliestShutdownDate": null, "sourceUrls": [ "https://console.groq.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "groq/gemma-7b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "groq", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-8, "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://console.groq.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "groq/groq/meta-llama/llama-guard-4-12b", "slug": "groq-groq-meta-llama-llama-guard-4-12b", "provider": "Groq", "providerSlug": "groq", "name": "llama-guard-4-12b", "displayName": "llama-guard-4-12b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/meta-llama/llama-guard-4-12b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "groq", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-7 } }, { "id": "groq/groq/meta-llama/llama-4-maverick-17b-128e-instruct", "slug": "groq-groq-meta-llama-llama-4-maverick-17b-128e-instruct", "provider": "Groq", "providerSlug": "groq", "name": "llama-4-maverick-17b-128e-instruct", "displayName": "llama-4-maverick-17b-128e-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/meta-llama/llama-4-maverick-17b-128e-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "groq/groq/meta-llama/llama-4-scout-17b-16e-instruct", "slug": "groq-groq-meta-llama-llama-4-scout-17b-16e-instruct", "provider": "Groq", "providerSlug": "groq", "name": "llama-4-scout-17b-16e-instruct", "displayName": "llama-4-scout-17b-16e-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.11, "outputUsdPer1MTokens": 0.33999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.11, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.1e-7, "output_cost_per_token": 3.4e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/meta-llama/llama-4-scout-17b-16e-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.1e-7, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.4e-7, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "groq/groq/moonshotai/kimi-k2-instruct-0905", "slug": "groq-groq-moonshotai-kimi-k2-instruct-0905", "provider": "Groq", "providerSlug": "groq", "name": "kimi-k2-instruct-0905", "displayName": "kimi-k2-instruct-0905", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "cache_read_input_token_cost": 5e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 262144, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/moonshotai/kimi-k2-instruct-0905", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "cache_read_input_token_cost": 5e-7, "litellm_provider": "groq", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true } }, { "id": "groq/groq/openai/gpt-oss-120b", "slug": "groq-groq-openai-gpt-oss-120b", "provider": "Groq", "providerSlug": "groq", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 32766, "maxInputTokens": 131072, "maxOutputTokens": 32766, "maxTokens": 32766, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/openai/gpt-oss-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 32766, "max_tokens": 32766, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "groq/groq/openai/gpt-oss-20b", "slug": "groq-groq-openai-gpt-oss-20b", "provider": "Groq", "providerSlug": "groq", "name": "gpt-oss-20b", "displayName": "gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": 0.0375, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3.75e-8, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/openai/gpt-oss-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 3.75e-8, "input_cost_per_token": 7.5e-8, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "groq/groq/openai/gpt-oss-safeguard-20b", "slug": "groq-groq-openai-gpt-oss-safeguard-20b", "provider": "Groq", "providerSlug": "groq", "name": "gpt-oss-safeguard-20b", "displayName": "gpt-oss-safeguard-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": 0.037, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3.7e-8, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 131072, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/openai/gpt-oss-safeguard-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 3.7e-8, "input_cost_per_token": 7.5e-8, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "benchmarks": { "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "groq/groq/playai-tts", "slug": "groq-groq-playai-tts", "provider": "Groq", "providerSlug": "groq", "name": "playai-tts", "displayName": "playai-tts", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00005, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00005 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 10000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2025-12-23", "shutdownDate": "2025-12-31", "earliestShutdownDate": null, "sourceUrls": [ "https://console.groq.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "groq/playai-tts", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.00005, "litellm_provider": "groq", "max_input_tokens": 10000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "audio_speech", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://console.groq.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "groq/groq/qwen/qwen3-32b", "slug": "groq-groq-qwen-qwen3-32b", "provider": "Groq", "providerSlug": "groq", "name": "qwen3-32b", "displayName": "qwen3-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.29, "outputUsdPer1MTokens": 0.59, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.29, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.9e-7, "output_cost_per_token": 5.9e-7 } }, "limits": { "contextWindow": 131000, "maxInputTokens": 131000, "maxOutputTokens": 131000, "maxTokens": 131000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": false, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/qwen/qwen3-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.9e-7, "litellm_provider": "groq", "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 5.9e-7, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true } }, { "id": "groq/groq/whisper-large-v3", "slug": "groq-groq-whisper-large-v3", "provider": "Groq", "providerSlug": "groq", "name": "whisper-large-v3", "displayName": "whisper-large-v3", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00003083, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00003083, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/whisper-large-v3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.00003083, "litellm_provider": "groq", "mode": "audio_transcription", "output_cost_per_second": 0, "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "groq/groq/whisper-large-v3-turbo", "slug": "groq-groq-whisper-large-v3-turbo", "provider": "Groq", "providerSlug": "groq", "name": "whisper-large-v3-turbo", "displayName": "whisper-large-v3-turbo", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.00001111, "perSecondOutputUsd": 0, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.00001111, "output_cost_per_second": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "groq/whisper-large-v3-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.00001111, "litellm_provider": "groq", "mode": "audio_transcription", "output_cost_per_second": 0, "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "openai/hd/1024-x-1024/dall-e-3", "slug": "openai-hd-1024-x-1024-dall-e-3", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-3", "displayName": "dall-e-3 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 7.629e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 7.629e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hd/1024-x-1024/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 7.629e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0 } }, { "id": "openai/hd/1024-x-1792/dall-e-3", "slug": "openai-hd-1024-x-1792-dall-e-3", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-3", "displayName": "dall-e-3 (1024x1792)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 6.539e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 6.539e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hd/1024-x-1792/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 6.539e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0 } }, { "id": "openai/hd/1792-x-1024/dall-e-3", "slug": "openai-hd-1792-x-1024-dall-e-3", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-3", "displayName": "dall-e-3 (1792x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 6.539e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 6.539e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hd/1792-x-1024/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 6.539e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0 } }, { "id": "heroku/heroku/claude-3-5-haiku", "slug": "heroku-heroku-claude-3-5-haiku", "provider": "heroku", "providerSlug": "heroku", "name": "claude-3-5-haiku", "displayName": "claude-3-5-haiku", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "heroku/claude-3-5-haiku", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "heroku", "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "max_input_tokens": 200000, "max_output_tokens": 8192 }, "benchmarks": { "aidercodeeditingleaderboard_score_claude35haiku20241022_benchmarkleaderboard_68": { "label": "Aider Code Editing", "category": "coding", "score": 75.2, "scoreText": "75.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Haiku", "exactModelOrSnapshot": "claude-3-5-haiku-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." } } }, { "id": "heroku/heroku/claude-3-5-sonnet-latest", "slug": "heroku-heroku-claude-3-5-sonnet-latest", "provider": "heroku", "providerSlug": "heroku", "name": "claude-3-5-sonnet-latest", "displayName": "claude-3-5-sonnet-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "heroku/claude-3-5-sonnet-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "heroku", "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "max_input_tokens": 200000, "max_output_tokens": 8192 }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "heroku/heroku/claude-3-7-sonnet", "slug": "heroku-heroku-claude-3-7-sonnet", "provider": "heroku", "providerSlug": "heroku", "name": "claude-3-7-sonnet", "displayName": "claude-3-7-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "heroku/claude-3-7-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "heroku", "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "max_input_tokens": 200000, "max_output_tokens": 8192 }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "heroku/heroku/claude-4-sonnet", "slug": "heroku-heroku-claude-4-sonnet", "provider": "heroku", "providerSlug": "heroku", "name": "claude-4-sonnet", "displayName": "claude-4-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "heroku/claude-4-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "heroku", "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "max_input_tokens": 200000, "max_output_tokens": 8192 } }, { "id": "openai/high/1024-x-1024/gpt-image-1", "slug": "openai-high-1024-x-1024-gpt-image-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 167000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.59263611e-7, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.167, "input_cost_per_pixel": 1.59263611e-7, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "high/1024-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.167, "input_cost_per_pixel": 1.59263611e-7, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/high/1024-x-1536/gpt-image-1", "slug": "openai-high-1024-x-1536-gpt-image-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 250000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.58945719e-7, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-7, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "high/1024-x-1536/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-7, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/high/1536-x-1024/gpt-image-1", "slug": "openai-high-1536-x-1024-gpt-image-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1", "displayName": "gpt-image-1 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 250000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.58945719e-7, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-7, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "high/1536-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-7, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "hyperbolic/hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B", "slug": "hyperbolic-hyperbolic-nousresearch-hermes-3-llama-3-1-70b", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Hermes-3-Llama-3.1-70B", "displayName": "Hermes-3-Llama-3.1-70B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "hyperbolic/hyperbolic/Qwen/QwQ-32B", "slug": "hyperbolic-hyperbolic-qwen-qwq-32b", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "QwQ-32B", "displayName": "QwQ-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/Qwen/QwQ-32B", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "hyperbolic/hyperbolic/Qwen/Qwen2.5-72B-Instruct", "slug": "hyperbolic-hyperbolic-qwen-qwen2-5-72b-instruct", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Qwen2.5-72B-Instruct", "displayName": "Qwen2.5-72B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/Qwen/Qwen2.5-72B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." } } }, { "id": "hyperbolic/hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct", "slug": "hyperbolic-hyperbolic-qwen-qwen2-5-coder-32b-instruct", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Qwen2.5-Coder-32B-Instruct", "displayName": "Qwen2.5-Coder-32B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_aiderpolyglot_percentcorrect_qwen25coder32binstruct_benchmarkleaderboard_247": { "label": "Aider Polyglot", "category": "agentic", "score": 16.4, "scoreText": "16.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-Coder", "exactModelOrSnapshot": "Qwen2.5-Coder-32B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the 32B instruct checkpoint." } } }, { "id": "hyperbolic/hyperbolic/Qwen/Qwen3-235B-A22B", "slug": "hyperbolic-hyperbolic-qwen-qwen3-235b-a22b", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Qwen3-235B-A22B", "displayName": "Qwen3-235B-A22B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/Qwen/Qwen3-235B-A22B", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "hyperbolic/hyperbolic/deepseek-ai/DeepSeek-R1", "slug": "hyperbolic-hyperbolic-deepseek-ai-deepseek-r1", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "DeepSeek-R1", "displayName": "DeepSeek-R1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/deepseek-ai/DeepSeek-R1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "hyperbolic/hyperbolic/deepseek-ai/DeepSeek-R1-0528", "slug": "hyperbolic-hyperbolic-deepseek-ai-deepseek-r1-0528", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "DeepSeek-R1-0528", "displayName": "DeepSeek-R1-0528", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/deepseek-ai/DeepSeek-R1-0528", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "hyperbolic/hyperbolic/deepseek-ai/DeepSeek-V3", "slug": "hyperbolic-hyperbolic-deepseek-ai-deepseek-v3", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "DeepSeek-V3", "displayName": "DeepSeek-V3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/deepseek-ai/DeepSeek-V3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "hyperbolic/hyperbolic/deepseek-ai/DeepSeek-V3-0324", "slug": "hyperbolic-hyperbolic-deepseek-ai-deepseek-v3-0324", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "DeepSeek-V3-0324", "displayName": "DeepSeek-V3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/deepseek-ai/DeepSeek-V3-0324", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "hyperbolic/hyperbolic/meta-llama/Llama-3.2-3B-Instruct", "slug": "hyperbolic-hyperbolic-meta-llama-llama-3-2-3b-instruct", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Llama-3.2-3B-Instruct", "displayName": "Llama-3.2-3B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/meta-llama/Llama-3.2-3B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "hyperbolic/hyperbolic/meta-llama/Llama-3.3-70B-Instruct", "slug": "hyperbolic-hyperbolic-meta-llama-llama-3-3-70b-instruct", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/meta-llama/Llama-3.3-70B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "hyperbolic/hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct", "slug": "hyperbolic-hyperbolic-meta-llama-meta-llama-3-70b-instruct", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Meta-Llama-3-70B-Instruct", "displayName": "Meta-Llama-3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "hyperbolic/hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct", "slug": "hyperbolic-hyperbolic-meta-llama-meta-llama-3-1-405b-instruct", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Meta-Llama-3.1-405B-Instruct", "displayName": "Meta-Llama-3.1-405B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "hyperbolic/hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct", "slug": "hyperbolic-hyperbolic-meta-llama-meta-llama-3-1-70b-instruct", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Meta-Llama-3.1-70B-Instruct", "displayName": "Meta-Llama-3.1-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "hyperbolic/hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct", "slug": "hyperbolic-hyperbolic-meta-llama-meta-llama-3-1-8b-instruct", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Meta-Llama-3.1-8B-Instruct", "displayName": "Meta-Llama-3.1-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "hyperbolic/hyperbolic/moonshotai/Kimi-K2-Instruct", "slug": "hyperbolic-hyperbolic-moonshotai-kimi-k2-instruct", "provider": "hyperbolic", "providerSlug": "hyperbolic", "name": "Kimi-K2-Instruct", "displayName": "Kimi-K2-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "hyperbolic/moonshotai/Kimi-K2-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "ai21/j2-light", "slug": "ai21-j2-light", "provider": "ai21", "providerSlug": "ai21", "name": "j2-light", "displayName": "j2-light", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "j2-light", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.000003 } }, { "id": "ai21/j2-mid", "slug": "ai21-j2-mid", "provider": "ai21", "providerSlug": "ai21", "name": "j2-mid", "displayName": "j2-mid", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "j2-mid", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.00001 } }, { "id": "ai21/j2-ultra", "slug": "ai21-j2-ultra", "provider": "ai21", "providerSlug": "ai21", "name": "j2-ultra", "displayName": "j2-ultra", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "j2-ultra", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.000015 } }, { "id": "ai21/jamba-1.5", "slug": "ai21-jamba-1-5", "provider": "ai21", "providerSlug": "ai21", "name": "jamba-1.5", "displayName": "jamba-1.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jamba-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-7, "supports_tool_choice": true } }, { "id": "ai21/jamba-1.5-large", "slug": "ai21-jamba-1-5-large", "provider": "ai21", "providerSlug": "ai21", "name": "jamba-1.5-large", "displayName": "jamba-1.5-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jamba-1.5-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000008, "supports_tool_choice": true } }, { "id": "ai21/jamba-1.5-large@001", "slug": "ai21-jamba-1-5-large-001", "provider": "ai21", "providerSlug": "ai21", "name": "jamba-1.5-large@001", "displayName": "jamba-1.5-large@001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jamba-1.5-large@001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000008, "supports_tool_choice": true } }, { "id": "ai21/jamba-1.5-mini", "slug": "ai21-jamba-1-5-mini", "provider": "ai21", "providerSlug": "ai21", "name": "jamba-1.5-mini", "displayName": "jamba-1.5-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jamba-1.5-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-7, "supports_tool_choice": true } }, { "id": "ai21/jamba-1.5-mini@001", "slug": "ai21-jamba-1-5-mini-001", "provider": "ai21", "providerSlug": "ai21", "name": "jamba-1.5-mini@001", "displayName": "jamba-1.5-mini@001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jamba-1.5-mini@001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-7, "supports_tool_choice": true } }, { "id": "ai21/jamba-large-1.6", "slug": "ai21-jamba-large-1-6", "provider": "ai21", "providerSlug": "ai21", "name": "jamba-large-1.6", "displayName": "jamba-large-1.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jamba-large-1.6", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000008, "supports_tool_choice": true } }, { "id": "ai21/jamba-large-1.7", "slug": "ai21-jamba-large-1-7", "provider": "ai21", "providerSlug": "ai21", "name": "jamba-large-1.7", "displayName": "jamba-large-1.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jamba-large-1.7", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000008, "supports_tool_choice": true } }, { "id": "ai21/jamba-mini-1.6", "slug": "ai21-jamba-mini-1-6", "provider": "ai21", "providerSlug": "ai21", "name": "jamba-mini-1.6", "displayName": "jamba-mini-1.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jamba-mini-1.6", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-7, "supports_tool_choice": true } }, { "id": "ai21/jamba-mini-1.7", "slug": "ai21-jamba-mini-1-7", "provider": "ai21", "providerSlug": "ai21", "name": "jamba-mini-1.7", "displayName": "jamba-mini-1.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jamba-mini-1.7", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-7, "supports_tool_choice": true } }, { "id": "jina_ai/jina-reranker-v2-base-multilingual", "slug": "jina_ai-jina-reranker-v2-base-multilingual", "provider": "jina_ai", "providerSlug": "jina_ai", "name": "jina-reranker-v2-base-multilingual", "displayName": "jina-reranker-v2-base-multilingual", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": 0.018, "outputUsdPer1MTokens": 0.018, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.018, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-8, "output_cost_per_token": 1.8e-8 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": 2048, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jina-reranker-v2-base-multilingual", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.8e-8, "litellm_provider": "jina_ai", "max_document_chunks_per_query": 2048, "max_input_tokens": 1024, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "rerank", "output_cost_per_token": 1.8e-8, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "local_rerankerbenchmarktable_beir_jinarerankerv3_officialmodelcard_330": { "label": "Reranker benchmark table", "category": "other", "score": 61.94, "scoreText": "61.94", "metric": "BEIR", "higherIsBetter": true, "source_url": "https://huggingface.co/jinaai/jina-reranker-v3", "checked_at": "2026-05-31", "baseModelFamily": "jina-reranker", "exactModelOrSnapshot": "jina-reranker-v3", "modelDeveloper": "Jina AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published model-card table row." }, "local_rerankerbenchmarktable_miracl_jinarerankerv3_officialmodelcard_331": { "label": "Reranker benchmark table", "category": "other", "score": 66.83, "scoreText": "66.83", "metric": "MIRACL", "higherIsBetter": true, "source_url": "https://huggingface.co/jinaai/jina-reranker-v3", "checked_at": "2026-05-31", "baseModelFamily": "jina-reranker", "exactModelOrSnapshot": "jina-reranker-v3", "modelDeveloper": "Jina AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published model-card table row." }, "local_rerankerbenchmarktable_mkqa_jinarerankerv3_officialmodelcard_332": { "label": "Reranker benchmark table", "category": "other", "score": 67.92, "scoreText": "67.92", "metric": "MKQA", "higherIsBetter": true, "source_url": "https://huggingface.co/jinaai/jina-reranker-v3", "checked_at": "2026-05-31", "baseModelFamily": "jina-reranker", "exactModelOrSnapshot": "jina-reranker-v3", "modelDeveloper": "Jina AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published model-card table row." }, "local_rerankerbenchmarktable_coir_jinarerankerv3_officialmodelcard_333": { "label": "Reranker benchmark table", "category": "other", "score": 70.64, "scoreText": "70.64", "metric": "CoIR", "higherIsBetter": true, "source_url": "https://huggingface.co/jinaai/jina-reranker-v3", "checked_at": "2026-05-31", "baseModelFamily": "jina-reranker", "exactModelOrSnapshot": "jina-reranker-v3", "modelDeveloper": "Jina AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published model-card table row." } } }, { "id": "bedrock_converse/jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock_converse-jp-anthropic-claude-sonnet-4-5-20250929-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6.6000000000000005, "above200kOutputUsdPer1MTokens": 24.75, "above200kCachedInputUsdPer1MTokens": 0.66, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock_converse/jp.anthropic.claude-haiku-4-5-20251001-v1:0", "slug": "bedrock_converse-jp-anthropic-claude-haiku-4-5-20251001-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "jp.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "jp.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 5.5, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": 1.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000001375, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000055 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "jp.anthropic.claude-haiku-4-5-20251001-v1:0", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000001375, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000055, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "crusoe/crusoe/deepseek-ai/DeepSeek-R1-0528", "slug": "crusoe-crusoe-deepseek-ai-deepseek-r1-0528", "provider": "crusoe", "providerSlug": "crusoe", "name": "DeepSeek-R1-0528", "displayName": "DeepSeek-R1-0528", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000007 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "reasoning": true, "system_messages": true, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "crusoe/deepseek-ai/DeepSeek-R1-0528", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.000007, "supports_function_calling": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "crusoe/crusoe/deepseek-ai/DeepSeek-V3-0324", "slug": "crusoe-crusoe-deepseek-ai-deepseek-v3-0324", "provider": "crusoe", "providerSlug": "crusoe", "name": "DeepSeek-V3-0324", "displayName": "DeepSeek-V3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "crusoe/deepseek-ai/DeepSeek-V3-0324", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000015, "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "crusoe/crusoe/google/gemma-3-12b-it", "slug": "crusoe-crusoe-google-gemma-3-12b-it", "provider": "crusoe", "providerSlug": "crusoe", "name": "gemma-3-12b-it", "displayName": "gemma-3-12b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "crusoe/google/gemma-3-12b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "crusoe/crusoe/meta-llama/Llama-3.3-70B-Instruct", "slug": "crusoe-crusoe-meta-llama-llama-3-3-70b-instruct", "provider": "crusoe", "providerSlug": "crusoe", "name": "Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "crusoe/meta-llama/Llama-3.3-70B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "crusoe/crusoe/moonshotai/Kimi-K2-Thinking", "slug": "crusoe-crusoe-moonshotai-kimi-k2-thinking", "provider": "crusoe", "providerSlug": "crusoe", "name": "Kimi-K2-Thinking", "displayName": "Kimi-K2-Thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "reasoning": true, "system_messages": true, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "crusoe/moonshotai/Kimi-K2-Thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000025, "supports_function_calling": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false } }, { "id": "crusoe/crusoe/openai/gpt-oss-120b", "slug": "crusoe-crusoe-openai-gpt-oss-120b", "provider": "crusoe", "providerSlug": "crusoe", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "crusoe/openai/gpt-oss-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "crusoe/crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507", "slug": "crusoe-crusoe-qwen-qwen3-235b-a22b-instruct-2507", "provider": "crusoe", "providerSlug": "crusoe", "name": "Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen3-235B-A22B-Instruct-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "lambda_ai/lambda_ai/deepseek-llama3.3-70b", "slug": "lambda_ai-lambda_ai-deepseek-llama3-3-70b", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "deepseek-llama3.3-70b", "displayName": "deepseek-llama3.3-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/deepseek-llama3.3-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "lambda_ai/lambda_ai/deepseek-r1-0528", "slug": "lambda_ai-lambda_ai-deepseek-r1-0528", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "deepseek-r1-0528", "displayName": "deepseek-r1-0528", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/deepseek-r1-0528", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "lambda_ai/lambda_ai/deepseek-r1-671b", "slug": "lambda_ai-lambda_ai-deepseek-r1-671b", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "deepseek-r1-671b", "displayName": "deepseek-r1-671b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/deepseek-r1-671b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "lambda_ai/lambda_ai/deepseek-v3-0324", "slug": "lambda_ai-lambda_ai-deepseek-v3-0324", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "deepseek-v3-0324", "displayName": "deepseek-v3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/deepseek-v3-0324", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "lambda_ai/lambda_ai/hermes3-405b", "slug": "lambda_ai-lambda_ai-hermes3-405b", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "hermes3-405b", "displayName": "hermes3-405b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/hermes3-405b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "lambda_ai/lambda_ai/hermes3-70b", "slug": "lambda_ai-lambda_ai-hermes3-70b", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "hermes3-70b", "displayName": "hermes3-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/hermes3-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "lambda_ai/lambda_ai/hermes3-8b", "slug": "lambda_ai-lambda_ai-hermes3-8b", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "hermes3-8b", "displayName": "hermes3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.024999999999999998, "outputUsdPer1MTokens": 0.04, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.024999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-8, "output_cost_per_token": 4e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/hermes3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-8, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-8, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "lambda_ai/lambda_ai/lfm-40b", "slug": "lambda_ai-lambda_ai-lfm-40b", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "lfm-40b", "displayName": "lfm-40b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/lfm-40b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "lambda_ai/lambda_ai/lfm-7b", "slug": "lambda_ai-lambda_ai-lfm-7b", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "lfm-7b", "displayName": "lfm-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.024999999999999998, "outputUsdPer1MTokens": 0.04, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.024999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-8, "output_cost_per_token": 4e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/lfm-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-8, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-8, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "lambda_ai/lambda_ai/llama-4-maverick-17b-128e-instruct-fp8", "slug": "lambda_ai-lambda_ai-llama-4-maverick-17b-128e-instruct-fp8", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "llama-4-maverick-17b-128e-instruct-fp8", "displayName": "llama-4-maverick-17b-128e-instruct-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "lambda_ai/lambda_ai/llama-4-scout-17b-16e-instruct", "slug": "lambda_ai-lambda_ai-llama-4-scout-17b-16e-instruct", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "llama-4-scout-17b-16e-instruct", "displayName": "llama-4-scout-17b-16e-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 16384, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/llama-4-scout-17b-16e-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "lambda_ai", "max_input_tokens": 16384, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "lambda_ai/lambda_ai/llama3.1-405b-instruct-fp8", "slug": "lambda_ai-lambda_ai-llama3-1-405b-instruct-fp8", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "llama3.1-405b-instruct-fp8", "displayName": "llama3.1-405b-instruct-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/llama3.1-405b-instruct-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "lambda_ai/lambda_ai/llama3.1-70b-instruct-fp8", "slug": "lambda_ai-lambda_ai-llama3-1-70b-instruct-fp8", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "llama3.1-70b-instruct-fp8", "displayName": "llama3.1-70b-instruct-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/llama3.1-70b-instruct-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "lambda_ai/lambda_ai/llama3.1-8b-instruct", "slug": "lambda_ai-lambda_ai-llama3-1-8b-instruct", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "llama3.1-8b-instruct", "displayName": "llama3.1-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.024999999999999998, "outputUsdPer1MTokens": 0.04, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.024999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-8, "output_cost_per_token": 4e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/llama3.1-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-8, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-8, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "lambda_ai/lambda_ai/llama3.1-nemotron-70b-instruct-fp8", "slug": "lambda_ai-lambda_ai-llama3-1-nemotron-70b-instruct-fp8", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "llama3.1-nemotron-70b-instruct-fp8", "displayName": "llama3.1-nemotron-70b-instruct-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/llama3.1-nemotron-70b-instruct-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "lambda_ai/lambda_ai/llama3.2-11b-vision-instruct", "slug": "lambda_ai-lambda_ai-llama3-2-11b-vision-instruct", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "llama3.2-11b-vision-instruct", "displayName": "llama3.2-11b-vision-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.015, "outputUsdPer1MTokens": 0.024999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.015, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-8, "output_cost_per_token": 2.5e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/llama3.2-11b-vision-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-8, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-8, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "lambda_ai/lambda_ai/llama3.2-3b-instruct", "slug": "lambda_ai-lambda_ai-llama3-2-3b-instruct", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "llama3.2-3b-instruct", "displayName": "llama3.2-3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.015, "outputUsdPer1MTokens": 0.024999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.015, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-8, "output_cost_per_token": 2.5e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/llama3.2-3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-8, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-8, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "lambda_ai/lambda_ai/llama3.3-70b-instruct-fp8", "slug": "lambda_ai-lambda_ai-llama3-3-70b-instruct-fp8", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "llama3.3-70b-instruct-fp8", "displayName": "llama3.3-70b-instruct-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/llama3.3-70b-instruct-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "lambda_ai/lambda_ai/qwen25-coder-32b-instruct", "slug": "lambda_ai-lambda_ai-qwen25-coder-32b-instruct", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "qwen25-coder-32b-instruct", "displayName": "qwen25-coder-32b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/qwen25-coder-32b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_aiderpolyglot_percentcorrect_qwen25coder32binstruct_benchmarkleaderboard_247": { "label": "Aider Polyglot", "category": "agentic", "score": 16.4, "scoreText": "16.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-Coder", "exactModelOrSnapshot": "Qwen2.5-Coder-32B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the 32B instruct checkpoint." } } }, { "id": "lambda_ai/lambda_ai/qwen3-32b-fp8", "slug": "lambda_ai-lambda_ai-qwen3-32b-fp8", "provider": "lambda_ai", "providerSlug": "lambda_ai", "name": "qwen3-32b-fp8", "displayName": "qwen3-32b-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "lambda_ai/qwen3-32b-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/low/1024-x-1024/gpt-image-1", "slug": "openai-low-1024-x-1024-gpt-image-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 11000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.0490417e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.011, "input_cost_per_pixel": 1.0490417e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1024-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.011, "input_cost_per_pixel": 1.0490417e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/low/1024-x-1536/gpt-image-1", "slug": "openai-low-1024-x-1536-gpt-image-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 16000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.0172526e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.016, "input_cost_per_pixel": 1.0172526e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1024-x-1536/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.016, "input_cost_per_pixel": 1.0172526e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/low/1536-x-1024/gpt-image-1", "slug": "openai-low-1536-x-1024-gpt-image-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1", "displayName": "gpt-image-1 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 16000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.0172526e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.016, "input_cost_per_pixel": 1.0172526e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1536-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.016, "input_cost_per_pixel": 1.0172526e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "bedrock/max-x-max/50-steps/stability.stable-diffusion-xl-v0", "slug": "bedrock-max-x-max-50-steps-stability-stable-diffusion-xl-v0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-diffusion-xl-v0", "displayName": "stability.stable-diffusion-xl-v0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 36000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.036 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "max-x-max/50-steps/stability.stable-diffusion-xl-v0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.036 } }, { "id": "bedrock/max-x-max/max-steps/stability.stable-diffusion-xl-v0", "slug": "bedrock-max-x-max-max-steps-stability-stable-diffusion-xl-v0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-diffusion-xl-v0", "displayName": "stability.stable-diffusion-xl-v0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 72000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.072 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "max-x-max/max-steps/stability.stable-diffusion-xl-v0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.072 } }, { "id": "openai/medium/1024-x-1024/gpt-image-1", "slug": "openai-medium-1024-x-1024-gpt-image-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 42000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 4.0054321e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.042, "input_cost_per_pixel": 4.0054321e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1024-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.042, "input_cost_per_pixel": 4.0054321e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/medium/1024-x-1536/gpt-image-1", "slug": "openai-medium-1024-x-1536-gpt-image-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1", "displayName": "gpt-image-1 (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 63000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 4.0054321e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.063, "input_cost_per_pixel": 4.0054321e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1024-x-1536/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.063, "input_cost_per_pixel": 4.0054321e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/medium/1536-x-1024/gpt-image-1", "slug": "openai-medium-1536-x-1024-gpt-image-1", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1", "displayName": "gpt-image-1 (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 63000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 4.0054321e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.063, "input_cost_per_pixel": 4.0054321e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1536-x-1024/gpt-image-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.063, "input_cost_per_pixel": 4.0054321e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/low/1024-x-1024/gpt-image-1-mini", "slug": "openai-low-1024-x-1024-gpt-image-1-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 5000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1024-x-1024/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.005, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/low/1024-x-1536/gpt-image-1-mini", "slug": "openai-low-1024-x-1536-gpt-image-1-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 6000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.006 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1024-x-1536/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.006, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/low/1536-x-1024/gpt-image-1-mini", "slug": "openai-low-1536-x-1024-gpt-image-1-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 6000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.006 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "low/1536-x-1024/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.006, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/medium/1024-x-1024/gpt-image-1-mini", "slug": "openai-medium-1024-x-1024-gpt-image-1-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 11000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.011 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1024-x-1024/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.011, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/medium/1024-x-1536/gpt-image-1-mini", "slug": "openai-medium-1024-x-1536-gpt-image-1-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1024x1536)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 15000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1024-x-1536/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.015, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "openai/medium/1536-x-1024/gpt-image-1-mini", "slug": "openai-medium-1536-x-1024-gpt-image-1-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-image-1-mini", "displayName": "gpt-image-1-mini (1536x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 15000, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medium/1536-x-1024/gpt-image-1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.015, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "vertex_ai-language-models/medlm-large", "slug": "vertex_ai-language-models-medlm-large", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "medlm-large", "displayName": "medlm-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.000005, "perCharacterOutputUsd": 0.000015, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.000005, "output_cost_per_character": 0.000015 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 8192, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medlm-large", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_character": 0.000005, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "chat", "output_cost_per_character": 0.000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true } }, { "id": "vertex_ai-language-models/medlm-medium", "slug": "vertex_ai-language-models-medlm-medium", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "medlm-medium", "displayName": "medlm-medium", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 5e-7, "perCharacterOutputUsd": 0.000001, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 5e-7, "output_cost_per_character": 0.000001 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "medlm-medium", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_character": 5e-7, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0.000001, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true } }, { "id": "bedrock/meta.llama2-13b-chat-v1", "slug": "bedrock-meta-llama2-13b-chat-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama2-13b-chat-v1", "displayName": "meta.llama2-13b-chat-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.75, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama2-13b-chat-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000001, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://aws.amazon.com/blogs/aws/amazon-bedrock-now-provides-access-to-llama-2-chat-13b-model/", "https://docs.aws.amazon.com/cdk/api/v2/java/software/amazon/awscdk/services/bedrock/FoundationModelIdentifier.html" ], "manual_model_modalities_note": "Bedrock exact model id from official docs." } }, { "id": "bedrock/meta.llama2-70b-chat-v1", "slug": "bedrock-meta-llama2-70b-chat-v1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama2-70b-chat-v1", "displayName": "meta.llama2-70b-chat-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.95, "outputUsdPer1MTokens": 2.56, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.95, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000195, "output_cost_per_token": 0.00000256 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama2-70b-chat-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000195, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000256, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/cdk/api/v2/java/software/amazon/awscdk/services/bedrock/FoundationModelIdentifier.html", "https://docs.aws.amazon.com/sagemaker/latest/dg/jumpstart-foundation-models-latest.html" ], "manual_model_modalities_note": "Bedrock exact model id from official docs." } }, { "id": "bedrock/meta.llama3-1-405b-instruct-v1:0", "slug": "bedrock-meta-llama3-1-405b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-1-405b-instruct-v1:0", "displayName": "meta.llama3-1-405b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.32, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.32, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000532, "output_cost_per_token": 0.000016 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama3-1-405b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000532, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000016, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-1-405b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "bedrock/meta.llama3-1-70b-instruct-v1:0", "slug": "bedrock-meta-llama3-1-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-1-70b-instruct-v1:0", "displayName": "meta.llama3-1-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.9900000000000001, "outputUsdPer1MTokens": 0.9900000000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.9900000000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9.9e-7, "output_cost_per_token": 9.9e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama3-1-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9.9e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 9.9e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-1-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "bedrock/meta.llama3-1-8b-instruct-v1:0", "slug": "bedrock-meta-llama3-1-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-1-8b-instruct-v1:0", "displayName": "meta.llama3-1-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.22, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 2.2e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama3-1-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 2.2e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-1-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "bedrock/meta.llama3-2-11b-instruct-v1:0", "slug": "bedrock-meta-llama3-2-11b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-2-11b-instruct-v1:0", "displayName": "meta.llama3-2-11b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 0.35, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama3-2-11b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.5e-7, "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-11b-instruct.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-meta.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "bedrock/meta.llama3-2-1b-instruct-v1:0", "slug": "bedrock-meta-llama3-2-1b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-2-1b-instruct-v1:0", "displayName": "meta.llama3-2-1b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama3-2-1b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "bedrock/meta.llama3-2-3b-instruct-v1:0", "slug": "bedrock-meta-llama3-2-3b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-2-3b-instruct-v1:0", "displayName": "meta.llama3-2-3b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama3-2-3b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "bedrock/meta.llama3-2-90b-instruct-v1:0", "slug": "bedrock-meta-llama3-2-90b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-2-90b-instruct-v1:0", "displayName": "meta.llama3-2-90b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama3-2-90b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-90b-instruct.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-meta.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "bedrock_converse/meta.llama3-3-70b-instruct-v1:0", "slug": "bedrock_converse-meta-llama3-3-70b-instruct-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "meta.llama3-3-70b-instruct-v1:0", "displayName": "meta.llama3-3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama3-3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock Converse exact Meta route id from official docs" }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "bedrock/meta.llama3-70b-instruct-v1:0", "slug": "bedrock-meta-llama3-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-70b-instruct-v1:0", "displayName": "meta.llama3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.65, "outputUsdPer1MTokens": 3.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000265, "output_cost_per_token": 0.0000035 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000265, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000035, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock/meta.llama3-8b-instruct-v1:0", "slug": "bedrock-meta-llama3-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "meta.llama3-8b-instruct-v1:0", "displayName": "meta.llama3-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama3-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Meta route id from official docs" } }, { "id": "bedrock_converse/meta.llama4-maverick-17b-instruct-v1:0", "slug": "bedrock_converse-meta-llama4-maverick-17b-instruct-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "meta.llama4-maverick-17b-instruct-v1:0", "displayName": "meta.llama4-maverick-17b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.24, "outputUsdPer1MTokens": 0.9700000000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.24, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.12, "batchOutputUsdPer1MTokens": 0.48500000000000004, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.4e-7, "input_cost_per_token_batches": 1.2e-7, "output_cost_per_token": 9.7e-7, "output_cost_per_token_batches": 4.85e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama4-maverick-17b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.4e-7, "input_cost_per_token_batches": 1.2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9.7e-7, "output_cost_per_token_batches": 4.85e-7, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.html" ], "manual_model_modalities_note": "Bedrock Converse exact Meta route id from official docs" }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "bedrock_converse/meta.llama4-scout-17b-instruct-v1:0", "slug": "bedrock_converse-meta-llama4-scout-17b-instruct-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "meta.llama4-scout-17b-instruct-v1:0", "displayName": "meta.llama4-scout-17b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.16999999999999998, "outputUsdPer1MTokens": 0.66, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.16999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.08499999999999999, "batchOutputUsdPer1MTokens": 0.33, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.7e-7, "input_cost_per_token_batches": 8.5e-8, "output_cost_per_token": 6.6e-7, "output_cost_per_token_batches": 3.3e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta.llama4-scout-17b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.7e-7, "input_cost_per_token_batches": 8.5e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.6e-7, "output_cost_per_token_batches": 3.3e-7, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.html" ], "manual_model_modalities_note": "Bedrock Converse exact Meta route id from official docs" }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "meta_llama/meta_llama/Llama-3.3-70B-Instruct", "slug": "meta_llama-meta_llama-llama-3-3-70b-instruct", "provider": "meta_llama", "providerSlug": "meta_llama", "name": "Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4028, "maxInputTokens": 128000, "maxOutputTokens": 4028, "maxTokens": 4028, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta_llama/Llama-3.3-70B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://llama.developer.meta.com/docs/models" }, "rawLitellm": { "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, "max_tokens": 4028, "mode": "chat", "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "meta_llama/meta_llama/Llama-3.3-8B-Instruct", "slug": "meta_llama-meta_llama-llama-3-3-8b-instruct", "provider": "meta_llama", "providerSlug": "meta_llama", "name": "Llama-3.3-8B-Instruct", "displayName": "Llama-3.3-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4028, "maxInputTokens": 128000, "maxOutputTokens": 4028, "maxTokens": 4028, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta_llama/Llama-3.3-8B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://llama.developer.meta.com/docs/models" }, "rawLitellm": { "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, "max_tokens": 4028, "mode": "chat", "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "meta_llama/meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "slug": "meta_llama-meta_llama-llama-4-maverick-17b-128e-instruct-fp8", "provider": "meta_llama", "providerSlug": "meta_llama", "name": "Llama-4-Maverick-17B-128E-Instruct-FP8", "displayName": "Llama-4-Maverick-17B-128E-Instruct-FP8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4028, "maxInputTokens": 1000000, "maxOutputTokens": 4028, "maxTokens": 4028, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "syncedAt": "2026-05-28", "sourceUrl": "https://llama.developer.meta.com/docs/models" }, "rawLitellm": { "litellm_provider": "meta_llama", "max_input_tokens": 1000000, "max_output_tokens": 4028, "max_tokens": 4028, "mode": "chat", "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "meta_llama/meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8", "slug": "meta_llama-meta_llama-llama-4-scout-17b-16e-instruct-fp8", "provider": "meta_llama", "providerSlug": "meta_llama", "name": "Llama-4-Scout-17B-16E-Instruct-FP8", "displayName": "Llama-4-Scout-17B-16E-Instruct-FP8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 4028, "maxInputTokens": 10000000, "maxOutputTokens": 4028, "maxTokens": 4028, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8", "syncedAt": "2026-05-28", "sourceUrl": "https://llama.developer.meta.com/docs/models" }, "rawLitellm": { "litellm_provider": "meta_llama", "max_input_tokens": 10000000, "max_output_tokens": 4028, "max_tokens": 4028, "mode": "chat", "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "bedrock_converse/minimax.minimax-m2", "slug": "bedrock_converse-minimax-minimax-m2", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "minimax.minimax-m2", "displayName": "minimax.minimax-m2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "native_structured_output": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax.minimax-m2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_system_messages": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2.html" ], "manual_model_modalities_note": "Bedrock Converse exact MiniMax route id from official docs" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock_converse/minimax.minimax-m2.1", "slug": "bedrock_converse-minimax-minimax-m2-1", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "minimax.minimax-m2.1", "displayName": "minimax.minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 196000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax.minimax-m2.1", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" ], "manual_model_modalities_note": "Bedrock Converse exact MiniMax route id from official docs" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "bedrock_converse/minimax.minimax-m2.5", "slug": "bedrock_converse-minimax-minimax-m2-5", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "minimax.minimax-m2.5", "displayName": "minimax.minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax.minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact MiniMax route id from official docs" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "minimax/minimax/speech-02-hd", "slug": "minimax-minimax-speech-02-hd", "provider": "minimax", "providerSlug": "minimax", "name": "speech-02-hd", "displayName": "speech-02-hd", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.0001, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.0001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax/speech-02-hd", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.0001, "litellm_provider": "minimax", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "minimax/minimax/speech-02-turbo", "slug": "minimax-minimax-speech-02-turbo", "provider": "minimax", "providerSlug": "minimax", "name": "speech-02-turbo", "displayName": "speech-02-turbo", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00006, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00006 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax/speech-02-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.00006, "litellm_provider": "minimax", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "minimax/minimax/speech-2.6-hd", "slug": "minimax-minimax-speech-2-6-hd", "provider": "minimax", "providerSlug": "minimax", "name": "speech-2.6-hd", "displayName": "speech-2.6-hd", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.0001, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.0001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax/speech-2.6-hd", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.0001, "litellm_provider": "minimax", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "minimax/minimax/speech-2.6-turbo", "slug": "minimax-minimax-speech-2-6-turbo", "provider": "minimax", "providerSlug": "minimax", "name": "speech-2.6-turbo", "displayName": "speech-2.6-turbo", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00006, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00006 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax/speech-2.6-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.00006, "litellm_provider": "minimax", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "minimax/minimax/MiniMax-M2.1", "slug": "minimax-minimax-minimax-m2-1", "provider": "minimax", "providerSlug": "minimax", "name": "MiniMax-M2.1", "displayName": "MiniMax-M2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": 0.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "prompt_caching": true, "reasoning": true, "system_messages": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax/MiniMax-M2.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 1000000, "max_output_tokens": 8192 }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "minimax/minimax/MiniMax-M2.1-lightning", "slug": "minimax-minimax-minimax-m2-1-lightning", "provider": "minimax", "providerSlug": "minimax", "name": "MiniMax-M2.1-lightning", "displayName": "MiniMax-M2.1-lightning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": 0.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "prompt_caching": true, "reasoning": true, "system_messages": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax/MiniMax-M2.1-lightning", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 1000000, "max_output_tokens": 8192 }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "minimax/minimax/MiniMax-M2.5", "slug": "minimax-minimax-minimax-m2-5", "provider": "minimax", "providerSlug": "minimax", "name": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": 0.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "prompt_caching": true, "reasoning": true, "system_messages": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax/MiniMax-M2.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 1000000, "max_output_tokens": 8192 }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "minimax/minimax/MiniMax-M2.5-lightning", "slug": "minimax-minimax-minimax-m2-5-lightning", "provider": "minimax", "providerSlug": "minimax", "name": "MiniMax-M2.5-lightning", "displayName": "MiniMax-M2.5-lightning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": 0.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": 1000000, "maxOutputTokens": 8192, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "prompt_caching": true, "reasoning": true, "system_messages": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax/MiniMax-M2.5-lightning", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 1000000, "max_output_tokens": 8192 }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "minimax/minimax/MiniMax-M2", "slug": "minimax-minimax-minimax-m2", "provider": "minimax", "providerSlug": "minimax", "name": "MiniMax-M2", "displayName": "MiniMax-M2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": 0.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "prompt_caching": true, "reasoning": true, "system_messages": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "minimax/MiniMax-M2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "cache_read_input_token_cost": 3e-8, "cache_creation_input_token_cost": 3.75e-7, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 200000, "max_output_tokens": 8192 }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "bedrock_converse/mistral.devstral-2-123b", "slug": "bedrock_converse-mistral-devstral-2-123b", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "mistral.devstral-2-123b", "displayName": "mistral.devstral-2-123b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 256000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.devstral-2-123b", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-devstral-2-123b.html" ], "manual_model_modalities_note": "Bedrock Converse exact Mistral route id from official docs" }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "bedrock_converse/mistral.magistral-small-2509", "slug": "bedrock_converse-mistral-magistral-small-2509", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "mistral.magistral-small-2509", "displayName": "mistral.magistral-small-2509", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.magistral-small-2509", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-magistral-small-2509.html" ], "manual_model_modalities_note": "Bedrock Converse exact Mistral route id from official docs" } }, { "id": "bedrock_converse/mistral.ministral-3-14b-instruct", "slug": "bedrock_converse-mistral-ministral-3-14b-instruct", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "mistral.ministral-3-14b-instruct", "displayName": "mistral.ministral-3-14b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.ministral-3-14b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-7, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-ministral-14b-3-0.html" ], "manual_model_modalities_note": "Bedrock Converse exact Mistral route id from official docs" } }, { "id": "bedrock_converse/mistral.ministral-3-3b-instruct", "slug": "bedrock_converse-mistral-ministral-3-3b-instruct", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "mistral.ministral-3-3b-instruct", "displayName": "mistral.ministral-3-3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.ministral-3-3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-ministral-3b.html" ], "manual_model_modalities_note": "Bedrock Converse exact Mistral route id from official docs" } }, { "id": "bedrock_converse/mistral.ministral-3-8b-instruct", "slug": "bedrock_converse-mistral-ministral-3-8b-instruct", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "mistral.ministral-3-8b-instruct", "displayName": "mistral.ministral-3-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.ministral-3-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-7, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-ministral-3-8b.html" ], "manual_model_modalities_note": "Bedrock Converse exact Mistral route id from official docs" } }, { "id": "bedrock/mistral.mistral-7b-instruct-v0:2", "slug": "bedrock-mistral-mistral-7b-instruct-v0-2", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mistral-7b-instruct-v0:2", "displayName": "mistral.mistral-7b-instruct-v0:2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.mistral-7b-instruct-v0:2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "bedrock/mistral.mistral-large-2402-v1:0", "slug": "bedrock-mistral-mistral-large-2402-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mistral-large-2402-v1:0", "displayName": "mistral.mistral-large-2402-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.mistral-large-2402-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" } }, { "id": "bedrock/mistral.mistral-large-2407-v1:0", "slug": "bedrock-mistral-mistral-large-2407-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mistral-large-2407-v1:0", "displayName": "mistral.mistral-large-2407-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 9, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000009 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 128000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.mistral-large-2407-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000009, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-mistral-large-2407.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" } }, { "id": "bedrock_converse/mistral.mistral-large-3-675b-instruct", "slug": "bedrock_converse-mistral-mistral-large-3-675b-instruct", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "mistral.mistral-large-3-675b-instruct", "displayName": "mistral.mistral-large-3-675b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.mistral-large-3-675b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large-3.html" ], "manual_model_modalities_note": "Bedrock Converse exact Mistral route id from official docs" }, "benchmarks": { "mmlu_accuracy_mistrallarge3_benchmarkleaderboard_118": { "label": "MMLU", "category": "general_knowledge", "score": 85.5, "scoreText": "85.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "mmlupro_accuracy_mistrallarge3_benchmarkleaderboard_119": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 78, "scoreText": "78.0", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "gpqadiamond_accuracy_mistrallarge3_benchmarkleaderboard_120": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 43.9, "scoreText": "43.9", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "humaneval_pass1_mistrallarge3_benchmarkleaderboard_121": { "label": "HumanEval", "category": "coding", "score": 92, "scoreText": "92.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "math500_accuracy_mistrallarge3_benchmarkleaderboard_122": { "label": "MATH-500", "category": "math", "score": 93.6, "scoreText": "93.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "aime2024_accuracy_mistrallarge3_benchmarkleaderboard_123": { "label": "AIME 2024", "category": "math", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "aime2025_accuracy_mistrallarge3_benchmarkleaderboard_124": { "label": "AIME 2025", "category": "math", "score": 40, "scoreText": "40.0", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "simpleqa_accuracy_mistrallarge3_benchmarkleaderboard_125": { "label": "SimpleQA", "category": "general_knowledge", "score": 23.8, "scoreText": "23.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." } } }, { "id": "bedrock/mistral.mistral-small-2402-v1:0", "slug": "bedrock-mistral-mistral-small-2402-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mistral-small-2402-v1:0", "displayName": "mistral.mistral-small-2402-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.mistral-small-2402-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-small.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" } }, { "id": "bedrock/mistral.mixtral-8x7b-instruct-v0:1", "slug": "bedrock-mistral-mixtral-8x7b-instruct-v0-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "mistral.mixtral-8x7b-instruct-v0:1", "displayName": "mistral.mixtral-8x7b-instruct-v0:1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.44999999999999996, "outputUsdPer1MTokens": 0.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.44999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.5e-7, "output_cost_per_token": 7e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.mixtral-8x7b-instruct-v0:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 7e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact Mistral route id from official docs" } }, { "id": "bedrock_converse/mistral.voxtral-mini-3b-2507", "slug": "bedrock_converse-mistral-voxtral-mini-3b-2507", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "mistral.voxtral-mini-3b-2507", "displayName": "mistral.voxtral-mini-3b-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.04, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "system_messages": true, "native_structured_output": true } }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.voxtral-mini-3b-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-8, "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-voxtral-mini-3b-2507.html" ], "manual_model_modalities_note": "Bedrock Converse exact Mistral route id from official docs" } }, { "id": "bedrock_converse/mistral.voxtral-small-24b-2507", "slug": "bedrock_converse-mistral-voxtral-small-24b-2507", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "mistral.voxtral-small-24b-2507", "displayName": "mistral.voxtral-small-24b-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "system_messages": true, "native_structured_output": true } }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral.voxtral-small-24b-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-7, "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-voxtral-small-24b-2507.html" ], "manual_model_modalities_note": "Bedrock Converse exact Mistral route id from official docs" } }, { "id": "mistral/mistral/codestral-2405", "slug": "mistral-mistral-codestral-2405", "provider": "Mistral", "providerSlug": "mistral", "name": "codestral-2405", "displayName": "codestral-2405", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2025-06-16", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/codestral-24-05" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Retirement date." }, "source": { "type": "litellm", "litellmKey": "mistral/codestral-2405", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000003, "supports_assistant_prefill": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/codestral-24-05", "https://docs.mistral.ai/models/codestral-25-08", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Codestral exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/codestral-24-05" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Retirement date." }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "mistral/mistral/codestral-2508", "slug": "mistral-mistral-codestral-2508", "provider": "Mistral", "providerSlug": "mistral", "name": "codestral-2508", "displayName": "codestral-2508", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/codestral-2508", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/codestral-25-08" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 9e-7, "source": "https://mistral.ai/news/codestral-25-08", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/codestral-24-05", "https://docs.mistral.ai/models/codestral-25-08", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Codestral exact ids from official docs" }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "mistral/mistral/codestral-latest", "slug": "mistral-mistral-codestral-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "codestral-latest", "displayName": "codestral-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/codestral-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000003, "supports_assistant_prefill": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/codestral-24-05", "https://docs.mistral.ai/models/codestral-25-08", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Codestral exact ids from official docs" }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "mistral/mistral/codestral-mamba-latest", "slug": "mistral-mistral-codestral-mamba-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "codestral-mamba-latest", "displayName": "codestral-mamba-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/codestral-mamba-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/technology/" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-7, "source": "https://mistral.ai/technology/", "supports_assistant_prefill": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "mistral/mistral/devstral-medium-2507", "slug": "mistral-mistral-devstral-medium-2507", "provider": "Mistral", "providerSlug": "mistral", "name": "devstral-medium-2507", "displayName": "devstral-medium-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-27", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/devstral-medium-1-0-25-07" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Deprecation date." }, "source": { "type": "litellm", "litellmKey": "mistral/devstral-medium-2507", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/devstral" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://mistral.ai/news/devstral", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/devstral-small-1-0-25-05", "https://docs.mistral.ai/models/devstral-small-1-1-25-07", "https://docs.mistral.ai/models/model-cards/devstral-medium-1-0-25-07", "https://docs.mistral.ai/models/devstral-2-25-12", "https://docs.mistral.ai/models/model-cards/devstral-small-2-25-12", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Devstral exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/devstral-medium-1-0-25-07" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Deprecation date." }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "mistral/mistral/devstral-small-2505", "slug": "mistral-mistral-devstral-small-2505", "provider": "Mistral", "providerSlug": "mistral", "name": "devstral-small-2505", "displayName": "devstral-small-2505", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/devstral-small-2505", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/devstral" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://mistral.ai/news/devstral", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/devstral-small-1-0-25-05", "https://docs.mistral.ai/models/devstral-small-1-1-25-07", "https://docs.mistral.ai/models/model-cards/devstral-medium-1-0-25-07", "https://docs.mistral.ai/models/devstral-2-25-12", "https://docs.mistral.ai/models/model-cards/devstral-small-2-25-12", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Devstral exact ids from official docs" }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "mistral/mistral/devstral-small-2507", "slug": "mistral-mistral-devstral-small-2507", "provider": "Mistral", "providerSlug": "mistral", "name": "devstral-small-2507", "displayName": "devstral-small-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/devstral-small-2507", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/devstral" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://mistral.ai/news/devstral", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/devstral-small-1-0-25-05", "https://docs.mistral.ai/models/devstral-small-1-1-25-07", "https://docs.mistral.ai/models/model-cards/devstral-medium-1-0-25-07", "https://docs.mistral.ai/models/devstral-2-25-12", "https://docs.mistral.ai/models/model-cards/devstral-small-2-25-12", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Devstral exact ids from official docs" }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "mistral/mistral/devstral-small-latest", "slug": "mistral-mistral-devstral-small-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "devstral-small-latest", "displayName": "devstral-small-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/devstral-small-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.mistral.ai/models/devstral-small-2-25-12" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/devstral-small-1-0-25-05", "https://docs.mistral.ai/models/devstral-small-1-1-25-07", "https://docs.mistral.ai/models/model-cards/devstral-medium-1-0-25-07", "https://docs.mistral.ai/models/devstral-2-25-12", "https://docs.mistral.ai/models/model-cards/devstral-small-2-25-12", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Devstral exact ids from official docs" }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "mistral/mistral/labs-devstral-small-2512", "slug": "mistral-mistral-labs-devstral-small-2512", "provider": "Mistral", "providerSlug": "mistral", "name": "labs-devstral-small-2512", "displayName": "labs-devstral-small-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-27", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/devstral-small-2-25-12" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Deprecation date." }, "source": { "type": "litellm", "litellmKey": "mistral/labs-devstral-small-2512", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.mistral.ai/models/devstral-small-2-25-12" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/devstral-small-1-0-25-05", "https://docs.mistral.ai/models/devstral-small-1-1-25-07", "https://docs.mistral.ai/models/model-cards/devstral-medium-1-0-25-07", "https://docs.mistral.ai/models/devstral-2-25-12", "https://docs.mistral.ai/models/model-cards/devstral-small-2-25-12", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Devstral exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/devstral-small-2-25-12" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Deprecation date." }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "mistral/mistral/devstral-latest", "slug": "mistral-mistral-devstral-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "devstral-latest", "displayName": "devstral-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/devstral-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/devstral-2-vibe-cli" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/devstral-small-1-0-25-05", "https://docs.mistral.ai/models/devstral-small-1-1-25-07", "https://docs.mistral.ai/models/model-cards/devstral-medium-1-0-25-07", "https://docs.mistral.ai/models/devstral-2-25-12", "https://docs.mistral.ai/models/model-cards/devstral-small-2-25-12", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Devstral exact ids from official docs" }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "mistral/mistral/devstral-medium-latest", "slug": "mistral-mistral-devstral-medium-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "devstral-medium-latest", "displayName": "devstral-medium-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/devstral-medium-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/devstral-2-vibe-cli" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/devstral-small-1-0-25-05", "https://docs.mistral.ai/models/devstral-small-1-1-25-07", "https://docs.mistral.ai/models/model-cards/devstral-medium-1-0-25-07", "https://docs.mistral.ai/models/devstral-2-25-12", "https://docs.mistral.ai/models/model-cards/devstral-small-2-25-12", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Devstral exact ids from official docs" }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "mistral/mistral/devstral-2512", "slug": "mistral-mistral-devstral-2512", "provider": "Mistral", "providerSlug": "mistral", "name": "devstral-2512", "displayName": "devstral-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-22", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/devstral-2-25-12" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Deprecation date." }, "source": { "type": "litellm", "litellmKey": "mistral/devstral-2512", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/devstral-2-vibe-cli" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/code_generation/", "https://docs.mistral.ai/models/model-cards/devstral-small-1-0-25-05", "https://docs.mistral.ai/models/devstral-small-1-1-25-07", "https://docs.mistral.ai/models/model-cards/devstral-medium-1-0-25-07", "https://docs.mistral.ai/models/devstral-2-25-12", "https://docs.mistral.ai/models/model-cards/devstral-small-2-25-12", "https://docs.mistral.ai/getting-started/changelog/" ], "manual_model_modalities_note": "Mistral Devstral exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/devstral-2-25-12" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Deprecation date." }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "mistral/mistral/magistral-medium-2506", "slug": "mistral-mistral-magistral-medium-2506", "provider": "Mistral", "providerSlug": "mistral", "name": "magistral-medium-2506", "displayName": "magistral-medium-2506", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 40000, "maxInputTokens": 40000, "maxOutputTokens": 40000, "maxTokens": 40000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/magistral-medium-2506", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/magistral" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "mistral", "max_input_tokens": 40000, "max_output_tokens": 40000, "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://mistral.ai/news/magistral", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/studio-api/conversations/reasoning/", "https://docs.mistral.ai/studio-api/conversations/reasoning/native", "https://docs.mistral.ai/models/model-cards/magistral-medium-1-0-25-06", "https://docs.mistral.ai/models/model-cards/magistral-small-1-0-25-06", "https://docs.mistral.ai/models/model-cards/magistral-medium-1-2-25-09", "https://docs.mistral.ai/models/model-cards/magistral-small-1-2-25-09" ], "manual_model_modalities_note": "Mistral Magistral exact ids from official docs" } }, { "id": "mistral/mistral/magistral-medium-2509", "slug": "mistral-mistral-magistral-medium-2509", "provider": "Mistral", "providerSlug": "mistral", "name": "magistral-medium-2509", "displayName": "magistral-medium-2509", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 40000, "maxInputTokens": 40000, "maxOutputTokens": 40000, "maxTokens": 40000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/magistral-medium-2509", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/magistral" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "mistral", "max_input_tokens": 40000, "max_output_tokens": 40000, "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://mistral.ai/news/magistral", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/studio-api/conversations/reasoning/", "https://docs.mistral.ai/studio-api/conversations/reasoning/native", "https://docs.mistral.ai/models/model-cards/magistral-medium-1-0-25-06", "https://docs.mistral.ai/models/model-cards/magistral-small-1-0-25-06", "https://docs.mistral.ai/models/model-cards/magistral-medium-1-2-25-09", "https://docs.mistral.ai/models/model-cards/magistral-small-1-2-25-09" ], "manual_model_modalities_note": "Mistral Magistral exact ids from official docs" } }, { "id": "mistral/mistral/magistral-medium-1-2-2509", "slug": "mistral-mistral-magistral-medium-1-2-2509", "provider": "Mistral", "providerSlug": "mistral", "name": "magistral-medium-1-2-2509", "displayName": "magistral-medium-1-2-2509", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 40000, "maxInputTokens": 40000, "maxOutputTokens": 40000, "maxTokens": 40000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/magistral-medium-1-2-2509", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/magistral" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "mistral", "max_input_tokens": 40000, "max_output_tokens": 40000, "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://mistral.ai/news/magistral", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true } }, { "id": "mistral/mistral/mistral-ocr-latest", "slug": "mistral-mistral-mistral-ocr-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-ocr-latest", "displayName": "mistral-ocr-latest", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": 0.001, "codeInterpreterUsdPerSession": null, "rawPricing": { "ocr_cost_per_page": 0.001, "annotation_cost_per_page": 0.003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [ "/v1/ocr" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-ocr-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing#api-pricing" }, "rawLitellm": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.001, "annotation_cost_per_page": 0.003, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://mistral.ai/pricing#api-pricing", "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "mistral/mistral/mistral-ocr-2505-completion", "slug": "mistral-mistral-mistral-ocr-2505-completion", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-ocr-2505-completion", "displayName": "mistral-ocr-2505-completion", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": 0.001, "codeInterpreterUsdPerSession": null, "rawPricing": { "ocr_cost_per_page": 0.001, "annotation_cost_per_page": 0.003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [ "/v1/ocr" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-ocr-2505-completion", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing#api-pricing" }, "rawLitellm": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.001, "annotation_cost_per_page": 0.003, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://mistral.ai/pricing#api-pricing", "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "mistral/mistral/magistral-medium-latest", "slug": "mistral-mistral-magistral-medium-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "magistral-medium-latest", "displayName": "magistral-medium-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 40000, "maxInputTokens": 40000, "maxOutputTokens": 40000, "maxTokens": 40000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/magistral-medium-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/magistral" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "mistral", "max_input_tokens": 40000, "max_output_tokens": 40000, "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://mistral.ai/news/magistral", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/studio-api/conversations/reasoning/", "https://docs.mistral.ai/studio-api/conversations/reasoning/native", "https://docs.mistral.ai/models/model-cards/magistral-medium-1-0-25-06", "https://docs.mistral.ai/models/model-cards/magistral-small-1-0-25-06", "https://docs.mistral.ai/models/model-cards/magistral-medium-1-2-25-09", "https://docs.mistral.ai/models/model-cards/magistral-small-1-2-25-09" ], "manual_model_modalities_note": "Mistral Magistral exact ids from official docs" } }, { "id": "mistral/mistral/magistral-small-2506", "slug": "mistral-mistral-magistral-small-2506", "provider": "Mistral", "providerSlug": "mistral", "name": "magistral-small-2506", "displayName": "magistral-small-2506", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 40000, "maxInputTokens": 40000, "maxOutputTokens": 40000, "maxTokens": 40000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/magistral-small-2506", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing#api-pricing" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "mistral", "max_input_tokens": 40000, "max_output_tokens": 40000, "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://mistral.ai/pricing#api-pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/studio-api/conversations/reasoning/", "https://docs.mistral.ai/studio-api/conversations/reasoning/native", "https://docs.mistral.ai/models/model-cards/magistral-medium-1-0-25-06", "https://docs.mistral.ai/models/model-cards/magistral-small-1-0-25-06", "https://docs.mistral.ai/models/model-cards/magistral-medium-1-2-25-09", "https://docs.mistral.ai/models/model-cards/magistral-small-1-2-25-09" ], "manual_model_modalities_note": "Mistral Magistral exact ids from official docs" } }, { "id": "mistral/mistral/magistral-small-latest", "slug": "mistral-mistral-magistral-small-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "magistral-small-latest", "displayName": "magistral-small-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 40000, "maxInputTokens": 40000, "maxOutputTokens": 40000, "maxTokens": 40000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/magistral-small-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing#api-pricing" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "mistral", "max_input_tokens": 40000, "max_output_tokens": 40000, "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://mistral.ai/pricing#api-pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/studio-api/conversations/reasoning/", "https://docs.mistral.ai/studio-api/conversations/reasoning/native", "https://docs.mistral.ai/models/model-cards/magistral-medium-1-0-25-06", "https://docs.mistral.ai/models/model-cards/magistral-small-1-0-25-06", "https://docs.mistral.ai/models/model-cards/magistral-medium-1-2-25-09", "https://docs.mistral.ai/models/model-cards/magistral-small-1-2-25-09" ], "manual_model_modalities_note": "Mistral Magistral exact ids from official docs" } }, { "id": "mistral/mistral/magistral-small-1-2-2509", "slug": "mistral-mistral-magistral-small-1-2-2509", "provider": "Mistral", "providerSlug": "mistral", "name": "magistral-small-1-2-2509", "displayName": "magistral-small-1-2-2509", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 40000, "maxInputTokens": 40000, "maxOutputTokens": 40000, "maxTokens": 40000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/magistral-small-1-2-2509", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing#api-pricing" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "mistral", "max_input_tokens": 40000, "max_output_tokens": 40000, "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://mistral.ai/pricing#api-pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true } }, { "id": "mistral/mistral/mistral-embed", "slug": "mistral-mistral-mistral-embed", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-embed", "displayName": "mistral-embed", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-embed", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "mistral", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding" } }, { "id": "mistral/mistral/codestral-embed", "slug": "mistral-mistral-codestral-embed", "provider": "Mistral", "providerSlug": "mistral", "name": "codestral-embed", "displayName": "codestral-embed", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/codestral-embed", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "mistral", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding" }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "mistral/mistral/codestral-embed-2505", "slug": "mistral-mistral-codestral-embed-2505", "provider": "Mistral", "providerSlug": "mistral", "name": "codestral-embed-2505", "displayName": "codestral-embed-2505", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/codestral-embed-2505", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "mistral", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding" }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "mistral/mistral/mistral-large-2402", "slug": "mistral-mistral-mistral-large-2402", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-large-2402", "displayName": "mistral-large-2402", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 4, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 4, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000012 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2025-06-16", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/mistral-large-1-0-24-02" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Retirement date." }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-large-2402", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000004, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000012, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/mistral-large-1-0-24-02" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Retirement date." } }, { "id": "mistral/mistral/mistral-large-2407", "slug": "mistral-mistral-mistral-large-2407", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-large-2407", "displayName": "mistral-large-2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 9, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000009 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2025-03-30", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/mistral-large-2-0-24-07" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Retirement date." }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-large-2407", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000009, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/mistral-large-2-0-24-07" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Retirement date." } }, { "id": "mistral/mistral/mistral-large-2411", "slug": "mistral-mistral-mistral-large-2411", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-large-2411", "displayName": "mistral-large-2411", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-27", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/mistral-large-2-1-24-11" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Deprecation date." }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-large-2411", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000006, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/mistral-large-2-1-24-11" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Deprecation date." } }, { "id": "mistral/mistral/mistral-large-latest", "slug": "mistral-mistral-mistral-large-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-large-latest", "displayName": "Mistral Large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-large-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.mistral.ai/models/mistral-large-3-25-12" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/vision/", "https://docs.mistral.ai/models/mistral-medium-3-25-05", "https://docs.mistral.ai/models/model-cards/mistral-medium-3-1-25-08", "https://docs.mistral.ai/models/mistral-large-3-25-12", "https://docs.mistral.ai/models/mistral-small-3-2-25-06", "https://docs.mistral.ai/models/ministral-3-8b-25-12", "https://docs.mistral.ai/models/pixtral-12b-24-09", "https://docs.mistral.ai/models/model-cards/pixtral-large-24-11" ], "manual_model_modalities_note": "Mistral vision-capable exact ids from official docs" } }, { "id": "mistral/mistral/mistral-large-3", "slug": "mistral-mistral-mistral-large-3", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-large-3", "displayName": "mistral-large-3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-large-3", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.mistral.ai/models/mistral-large-3-25-12" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmlu_accuracy_mistrallarge3_benchmarkleaderboard_118": { "label": "MMLU", "category": "general_knowledge", "score": 85.5, "scoreText": "85.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "mmlupro_accuracy_mistrallarge3_benchmarkleaderboard_119": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 78, "scoreText": "78.0", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "gpqadiamond_accuracy_mistrallarge3_benchmarkleaderboard_120": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 43.9, "scoreText": "43.9", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "humaneval_pass1_mistrallarge3_benchmarkleaderboard_121": { "label": "HumanEval", "category": "coding", "score": 92, "scoreText": "92.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "math500_accuracy_mistrallarge3_benchmarkleaderboard_122": { "label": "MATH-500", "category": "math", "score": 93.6, "scoreText": "93.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "aime2024_accuracy_mistrallarge3_benchmarkleaderboard_123": { "label": "AIME 2024", "category": "math", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "aime2025_accuracy_mistrallarge3_benchmarkleaderboard_124": { "label": "AIME 2025", "category": "math", "score": 40, "scoreText": "40.0", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "simpleqa_accuracy_mistrallarge3_benchmarkleaderboard_125": { "label": "SimpleQA", "category": "general_knowledge", "score": 23.8, "scoreText": "23.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." } } }, { "id": "mistral/mistral/mistral-large-2512", "slug": "mistral-mistral-mistral-large-2512", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-large-2512", "displayName": "mistral-large-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-large-2512", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.mistral.ai/models/mistral-large-3-25-12" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/vision/", "https://docs.mistral.ai/models/mistral-medium-3-25-05", "https://docs.mistral.ai/models/model-cards/mistral-medium-3-1-25-08", "https://docs.mistral.ai/models/mistral-large-3-25-12", "https://docs.mistral.ai/models/mistral-small-3-2-25-06", "https://docs.mistral.ai/models/ministral-3-8b-25-12", "https://docs.mistral.ai/models/pixtral-12b-24-09", "https://docs.mistral.ai/models/model-cards/pixtral-large-24-11" ], "manual_model_modalities_note": "Mistral vision-capable exact ids from official docs" } }, { "id": "mistral/mistral/mistral-medium", "slug": "mistral-mistral-mistral-medium", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-medium", "displayName": "mistral-medium", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.7, "outputUsdPer1MTokens": 8.1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000027, "output_cost_per_token": 0.0000081 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-medium", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000027, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0000081, "supports_assistant_prefill": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs" } }, { "id": "mistral/mistral/mistral-medium-2312", "slug": "mistral-mistral-mistral-medium-2312", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-medium-2312", "displayName": "mistral-medium-2312", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.7, "outputUsdPer1MTokens": 8.1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000027, "output_cost_per_token": 0.0000081 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2025-06-16", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/mistral-medium-1-0-23-12" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Retirement date." }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-medium-2312", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000027, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0000081, "supports_assistant_prefill": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/mistral-medium-1-0-23-12" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Retirement date." } }, { "id": "mistral/mistral/mistral-medium-2505", "slug": "mistral-mistral-mistral-medium-2505", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-medium-2505", "displayName": "mistral-medium-2505", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 131072, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-medium-2505", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000002, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/vision/", "https://docs.mistral.ai/models/mistral-medium-3-25-05", "https://docs.mistral.ai/models/model-cards/mistral-medium-3-1-25-08", "https://docs.mistral.ai/models/mistral-large-3-25-12", "https://docs.mistral.ai/models/mistral-small-3-2-25-06", "https://docs.mistral.ai/models/ministral-3-8b-25-12", "https://docs.mistral.ai/models/pixtral-12b-24-09", "https://docs.mistral.ai/models/model-cards/pixtral-large-24-11" ], "manual_model_modalities_note": "Mistral vision-capable exact ids from official docs" } }, { "id": "mistral/mistral/mistral-medium-latest", "slug": "mistral-mistral-mistral-medium-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-medium-latest", "displayName": "mistral-medium-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-medium-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000002, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/vision/", "https://docs.mistral.ai/models/mistral-medium-3-25-05", "https://docs.mistral.ai/models/model-cards/mistral-medium-3-1-25-08", "https://docs.mistral.ai/models/mistral-large-3-25-12", "https://docs.mistral.ai/models/mistral-small-3-2-25-06", "https://docs.mistral.ai/models/ministral-3-8b-25-12", "https://docs.mistral.ai/models/pixtral-12b-24-09", "https://docs.mistral.ai/models/model-cards/pixtral-large-24-11" ], "manual_model_modalities_note": "Mistral vision-capable exact ids from official docs" } }, { "id": "mistral/mistral/mistral-medium-3-1-2508", "slug": "mistral-mistral-mistral-medium-3-1-2508", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-medium-3-1-2508", "displayName": "mistral-medium-3-1-2508", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-medium-3-1-2508", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/news/mistral-medium-3" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://mistral.ai/news/mistral-medium-3", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "mistral/mistral/mistral-small", "slug": "mistral-mistral-mistral-small", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-small", "displayName": "mistral-small", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-7, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs" } }, { "id": "mistral/mistral/mistral-small-latest", "slug": "mistral-mistral-mistral-small-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-small-latest", "displayName": "mistral-small-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.18, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 1.8e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-small-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.8e-7, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/vision/", "https://docs.mistral.ai/models/mistral-medium-3-25-05", "https://docs.mistral.ai/models/model-cards/mistral-medium-3-1-25-08", "https://docs.mistral.ai/models/mistral-large-3-25-12", "https://docs.mistral.ai/models/mistral-small-3-2-25-06", "https://docs.mistral.ai/models/ministral-3-8b-25-12", "https://docs.mistral.ai/models/pixtral-12b-24-09", "https://docs.mistral.ai/models/model-cards/pixtral-large-24-11" ], "manual_model_modalities_note": "Mistral vision-capable exact ids from official docs" } }, { "id": "mistral/mistral/mistral-small-3-2-2506", "slug": "mistral-mistral-mistral-small-3-2-2506", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-small-3-2-2506", "displayName": "mistral-small-3-2-2506", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.18, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 1.8e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-small-3-2-2506", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.8e-7, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmlu_accuracy_mistralsmall3_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 81, "scoreText": "81%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mistral-small-3", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3", "exactModelOrSnapshot": "mistral-small-3", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is stated in the announcement text." } } }, { "id": "mistral/mistral/ministral-3-3b-2512", "slug": "mistral-mistral-ministral-3-3b-2512", "provider": "Mistral", "providerSlug": "mistral", "name": "ministral-3-3b-2512", "displayName": "ministral-3-3b-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/ministral-3-3b-2512", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-7, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "mistral/mistral/ministral-3-8b-2512", "slug": "mistral-mistral-ministral-3-8b-2512", "provider": "Mistral", "providerSlug": "mistral", "name": "ministral-3-8b-2512", "displayName": "ministral-3-8b-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/ministral-3-8b-2512", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-7, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "mistral/mistral/ministral-3-14b-2512", "slug": "mistral-mistral-ministral-3-14b-2512", "provider": "Mistral", "providerSlug": "mistral", "name": "ministral-3-14b-2512", "displayName": "ministral-3-14b-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/ministral-3-14b-2512", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "mistral/mistral/ministral-8b-2512", "slug": "mistral-mistral-ministral-8b-2512", "provider": "Mistral", "providerSlug": "mistral", "name": "ministral-8b-2512", "displayName": "ministral-8b-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/ministral-8b-2512", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-7, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/vision/", "https://docs.mistral.ai/models/mistral-medium-3-25-05", "https://docs.mistral.ai/models/model-cards/mistral-medium-3-1-25-08", "https://docs.mistral.ai/models/mistral-large-3-25-12", "https://docs.mistral.ai/models/mistral-small-3-2-25-06", "https://docs.mistral.ai/models/ministral-3-8b-25-12", "https://docs.mistral.ai/models/pixtral-12b-24-09", "https://docs.mistral.ai/models/model-cards/pixtral-large-24-11" ], "manual_model_modalities_note": "Mistral vision-capable exact ids from official docs" } }, { "id": "mistral/mistral/mistral-tiny", "slug": "mistral-mistral-mistral-tiny", "provider": "Mistral", "providerSlug": "mistral", "name": "mistral-tiny", "displayName": "mistral-tiny", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/mistral-tiny", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.5e-7, "supports_assistant_prefill": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs" } }, { "id": "mistral/mistral/open-codestral-mamba", "slug": "mistral-mistral-open-codestral-mamba", "provider": "Mistral", "providerSlug": "mistral", "name": "open-codestral-mamba", "displayName": "open-codestral-mamba", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/open-codestral-mamba", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/technology/" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-7, "source": "https://mistral.ai/technology/", "supports_assistant_prefill": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "mistral/mistral/open-mistral-7b", "slug": "mistral-mistral-open-mistral-7b", "provider": "Mistral", "providerSlug": "mistral", "name": "open-mistral-7b", "displayName": "open-mistral-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/open-mistral-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.5e-7, "supports_assistant_prefill": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs" }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "mistral/mistral/open-mistral-nemo", "slug": "mistral-mistral-open-mistral-nemo", "provider": "Mistral", "providerSlug": "mistral", "name": "open-mistral-nemo", "displayName": "open-mistral-nemo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/open-mistral-nemo", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/technology/" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://mistral.ai/technology/", "supports_assistant_prefill": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs" }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "mistral/mistral/open-mistral-nemo-2407", "slug": "mistral-mistral-open-mistral-nemo-2407", "provider": "Mistral", "providerSlug": "mistral", "name": "open-mistral-nemo-2407", "displayName": "open-mistral-nemo-2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-22", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/mistral-nemo-12b-24-07" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Deprecation date." }, "source": { "type": "litellm", "litellmKey": "mistral/open-mistral-nemo-2407", "syncedAt": "2026-05-28", "sourceUrl": "https://mistral.ai/technology/" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://mistral.ai/technology/", "supports_assistant_prefill": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/mistral-nemo-12b-24-07" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Deprecation date." }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "mistral/mistral/open-mixtral-8x22b", "slug": "mistral-mistral-open-mixtral-8x22b", "provider": "Mistral", "providerSlug": "mistral", "name": "open-mixtral-8x22b", "displayName": "open-mixtral-8x22b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 65336, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2025-03-30", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Retirement date." }, "source": { "type": "litellm", "litellmKey": "mistral/open-mixtral-8x22b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "mistral", "max_input_tokens": 65336, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000006, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Retirement date." }, "benchmarks": { "gsm8kmaj8_8shot_mixtral8x22binstruct_officiallaunchpost_212": { "label": "GSM8K maj@8", "category": "math", "score": 90.8, "scoreText": "90.8%", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on GSM8K maj@8." }, "mathmaj4_4shot_mixtral8x22binstruct_officiallaunchpost_213": { "label": "Math maj@4", "category": "math", "score": 44.6, "scoreText": "44.6%", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on Math maj@4." } } }, { "id": "mistral/mistral/open-mixtral-8x7b", "slug": "mistral-mistral-open-mixtral-8x7b", "provider": "Mistral", "providerSlug": "mistral", "name": "open-mixtral-8x7b", "displayName": "open-mixtral-8x7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7, "outputUsdPer1MTokens": 0.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-7, "output_cost_per_token": 7e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2025-03-30", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/mixtral-8x7b-0-1" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Retirement date." }, "source": { "type": "litellm", "litellmKey": "mistral/open-mixtral-8x7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-7, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 7e-7, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/getting-started/changelog/", "https://docs.mistral.ai/getting-started/models/models_overview/", "https://docs.mistral.ai/models/mistral-7b-0-3", "https://docs.mistral.ai/models/model-cards/mistral-nemo-12b-24-07", "https://docs.mistral.ai/models/mixtral-8x7b-0-1", "https://docs.mistral.ai/models/mixtral-8x22b-0-1-0-3", "https://docs.mistral.ai/models/mistral-large-1-0-24-02", "https://docs.mistral.ai/models/mistral-large-2-0-24-07", "https://docs.mistral.ai/models/model-cards/mistral-large-2-1-24-11", "https://docs.mistral.ai/models/mistral-medium-1-0-23-12", "https://docs.mistral.ai/models/mistral-small-1-0-24-02" ], "manual_model_modalities_note": "Mistral legacy/open chat exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/mixtral-8x7b-0-1" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Retirement date." } }, { "id": "mistral/mistral/pixtral-12b-2409", "slug": "mistral-mistral-pixtral-12b-2409", "provider": "Mistral", "providerSlug": "mistral", "name": "pixtral-12b-2409", "displayName": "pixtral-12b-2409", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/pixtral-12b-2409", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-7, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/vision/", "https://docs.mistral.ai/models/mistral-medium-3-25-05", "https://docs.mistral.ai/models/model-cards/mistral-medium-3-1-25-08", "https://docs.mistral.ai/models/mistral-large-3-25-12", "https://docs.mistral.ai/models/mistral-small-3-2-25-06", "https://docs.mistral.ai/models/ministral-3-8b-25-12", "https://docs.mistral.ai/models/pixtral-12b-24-09", "https://docs.mistral.ai/models/model-cards/pixtral-large-24-11" ], "manual_model_modalities_note": "Mistral vision-capable exact ids from official docs" } }, { "id": "mistral/mistral/pixtral-large-2411", "slug": "mistral-mistral-pixtral-large-2411", "provider": "Mistral", "providerSlug": "mistral", "name": "pixtral-large-2411", "displayName": "pixtral-large-2411", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-27", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.mistral.ai/models/pixtral-large-24-11" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Mistral model card labels this as Deprecation date." }, "source": { "type": "litellm", "litellmKey": "mistral/pixtral-large-2411", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000006, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/capabilities/vision/", "https://docs.mistral.ai/models/mistral-medium-3-25-05", "https://docs.mistral.ai/models/model-cards/mistral-medium-3-1-25-08", "https://docs.mistral.ai/models/mistral-large-3-25-12", "https://docs.mistral.ai/models/mistral-small-3-2-25-06", "https://docs.mistral.ai/models/ministral-3-8b-25-12", "https://docs.mistral.ai/models/pixtral-12b-24-09", "https://docs.mistral.ai/models/model-cards/pixtral-large-24-11" ], "manual_model_modalities_note": "Mistral vision-capable exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.mistral.ai/models/pixtral-large-24-11" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Mistral model card labels this as Deprecation date." } }, { "id": "mistral/mistral/pixtral-large-latest", "slug": "mistral-mistral-pixtral-large-latest", "provider": "Mistral", "providerSlug": "mistral", "name": "pixtral-large-latest", "displayName": "pixtral-large-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "mistral/pixtral-large-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000006, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "bedrock_converse/moonshot.kimi-k2-thinking", "slug": "bedrock_converse-moonshot-kimi-k2-thinking", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "moonshot.kimi-k2-thinking", "displayName": "moonshot.kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "system_messages": true, "native_structured_output": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot.kimi-k2-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000025, "supports_reasoning": true, "supports_system_messages": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" ], "manual_model_modalities_note": "Bedrock Converse exact Moonshot route id from official docs" } }, { "id": "bedrock_converse/moonshotai.kimi-k2.5", "slug": "bedrock_converse-moonshotai-kimi-k2-5", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "moonshotai.kimi-k2.5", "displayName": "moonshotai.kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshotai.kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Moonshot route id from official docs" }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "moonshot/moonshot/kimi-k2-0711-preview", "slug": "moonshot-moonshot-kimi-k2-0711-preview", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-k2-0711-preview", "displayName": "kimi-k2-0711-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-k2-0711-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true } }, { "id": "moonshot/moonshot/kimi-k2-0905-preview", "slug": "moonshot-moonshot-kimi-k2-0905-preview", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-k2-0905-preview", "displayName": "kimi-k2-0905-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-k2-0905-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true } }, { "id": "moonshot/moonshot/kimi-k2-turbo-preview", "slug": "moonshot-moonshot-kimi-k2-turbo-preview", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-k2-turbo-preview", "displayName": "kimi-k2-turbo-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.15, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.00000115, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-k2-turbo-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.00000115, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000008, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true } }, { "id": "moonshot/moonshot/kimi-k2.5", "slug": "moonshot-moonshot-kimi-k2-5", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-k2.5", "displayName": "kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "video_input": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart" }, "rawLitellm": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 6e-7, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "moonshot/moonshot/kimi-k2.6", "slug": "moonshot-moonshot-kimi-k2-6", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-k2.6", "displayName": "kimi-k2.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.95, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": 0.16, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.95, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.6e-7, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "video_input": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-k2.6", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.kimi.ai/docs/pricing/chat-k26" }, "rawLitellm": { "cache_read_input_token_cost": 1.6e-7, "input_cost_per_token": 9.5e-7, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000004, "source": "https://platform.kimi.ai/docs/pricing/chat-k26", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "benchmarks": { "gpqadiamond_score_kimik26_officialmodelcard_172": { "label": "GPQA Diamond", "category": "reasoning", "score": 90.5, "scoreText": "90.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.6", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.6", "exactModelOrSnapshot": "Kimi-K2.6", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchpro_score_kimik26_officialmodelcard_173": { "label": "SWE-bench Pro", "category": "coding", "score": 58.6, "scoreText": "58.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.6", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.6", "exactModelOrSnapshot": "Kimi-K2.6", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_browsecomp_score_kimik26_officialmodelcard_223": { "label": "BrowseComp", "category": "other", "score": 83.2, "scoreText": "83.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.6", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.6", "exactModelOrSnapshot": "Kimi-K2.6", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.6 benchmark table." }, "local_hlefullwtools_score_kimik26_officialmodelcard_224": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 54, "scoreText": "54.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.6", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.6", "exactModelOrSnapshot": "Kimi-K2.6", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.6 benchmark table." }, "local_terminalbench20terminus2_score_kimik26_officialmodelcard_225": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 66.7, "scoreText": "66.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.6", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.6", "exactModelOrSnapshot": "Kimi-K2.6", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.6 benchmark table." }, "local_swebenchverified_score_kimik26_officialmodelcard_226": { "label": "SWE-bench Verified", "category": "coding", "score": 80.2, "scoreText": "80.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.6", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.6", "exactModelOrSnapshot": "Kimi-K2.6", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.6 benchmark table." } } }, { "id": "moonshot/moonshot/kimi-latest", "slug": "moonshot-moonshot-kimi-latest", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-latest", "displayName": "kimi-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.000002, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "moonshot/moonshot/kimi-latest-128k", "slug": "moonshot-moonshot-kimi-latest-128k", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-latest-128k", "displayName": "kimi-latest-128k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-latest-128k", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.000002, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "moonshot/moonshot/kimi-latest-32k", "slug": "moonshot-moonshot-kimi-latest-32k", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-latest-32k", "displayName": "kimi-latest-32k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-latest-32k", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.000001, "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "moonshot/moonshot/kimi-latest-8k", "slug": "moonshot-moonshot-kimi-latest-8k", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-latest-8k", "displayName": "kimi-latest-8k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-latest-8k", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 2e-7, "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "moonshot/moonshot/kimi-thinking-preview", "slug": "moonshot-moonshot-kimi-thinking-preview", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-thinking-preview", "displayName": "kimi-thinking-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-thinking-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_vision": true } }, { "id": "moonshot/moonshot/kimi-k2-thinking", "slug": "moonshot-moonshot-kimi-k2-thinking", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-k2-thinking", "displayName": "kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-k2-thinking", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true } }, { "id": "moonshot/moonshot/kimi-k2-thinking-turbo", "slug": "moonshot-moonshot-kimi-k2-thinking-turbo", "provider": "moonshot", "providerSlug": "moonshot", "name": "kimi-k2-thinking-turbo", "displayName": "kimi-k2-thinking-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.15, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.00000115, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/kimi-k2-thinking-turbo", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.00000115, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000008, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true } }, { "id": "moonshot/moonshot/moonshot-v1-128k", "slug": "moonshot-moonshot-moonshot-v1-128k", "provider": "moonshot", "providerSlug": "moonshot", "name": "moonshot-v1-128k", "displayName": "moonshot-v1-128k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/moonshot-v1-128k", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "moonshot/moonshot/moonshot-v1-128k-0430", "slug": "moonshot-moonshot-moonshot-v1-128k-0430", "provider": "moonshot", "providerSlug": "moonshot", "name": "moonshot-v1-128k-0430", "displayName": "moonshot-v1-128k-0430", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/moonshot-v1-128k-0430", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "moonshot/moonshot/moonshot-v1-128k-vision-preview", "slug": "moonshot-moonshot-moonshot-v1-128k-vision-preview", "provider": "moonshot", "providerSlug": "moonshot", "name": "moonshot-v1-128k-vision-preview", "displayName": "moonshot-v1-128k-vision-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/moonshot-v1-128k-vision-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "moonshot/moonshot/moonshot-v1-32k", "slug": "moonshot-moonshot-moonshot-v1-32k", "provider": "moonshot", "providerSlug": "moonshot", "name": "moonshot-v1-32k", "displayName": "moonshot-v1-32k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/moonshot-v1-32k", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "moonshot/moonshot/moonshot-v1-32k-0430", "slug": "moonshot-moonshot-moonshot-v1-32k-0430", "provider": "moonshot", "providerSlug": "moonshot", "name": "moonshot-v1-32k-0430", "displayName": "moonshot-v1-32k-0430", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/moonshot-v1-32k-0430", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "moonshot/moonshot/moonshot-v1-32k-vision-preview", "slug": "moonshot-moonshot-moonshot-v1-32k-vision-preview", "provider": "moonshot", "providerSlug": "moonshot", "name": "moonshot-v1-32k-vision-preview", "displayName": "moonshot-v1-32k-vision-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/moonshot-v1-32k-vision-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "moonshot/moonshot/moonshot-v1-8k", "slug": "moonshot-moonshot-moonshot-v1-8k", "provider": "moonshot", "providerSlug": "moonshot", "name": "moonshot-v1-8k", "displayName": "moonshot-v1-8k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/moonshot-v1-8k", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "moonshot/moonshot/moonshot-v1-8k-0430", "slug": "moonshot-moonshot-moonshot-v1-8k-0430", "provider": "moonshot", "providerSlug": "moonshot", "name": "moonshot-v1-8k-0430", "displayName": "moonshot-v1-8k-0430", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/moonshot-v1-8k-0430", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "moonshot/moonshot/moonshot-v1-8k-vision-preview", "slug": "moonshot-moonshot-moonshot-v1-8k-vision-preview", "provider": "moonshot", "providerSlug": "moonshot", "name": "moonshot-v1-8k-vision-preview", "displayName": "moonshot-v1-8k-vision-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/moonshot-v1-8k-vision-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "moonshot/moonshot/moonshot-v1-auto", "slug": "moonshot-moonshot-moonshot-v1-auto", "provider": "moonshot", "providerSlug": "moonshot", "name": "moonshot-v1-auto", "displayName": "moonshot-v1-auto", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "moonshot/moonshot-v1-auto", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.moonshot.ai/docs/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "morph/morph/morph-v3-fast", "slug": "morph-morph-morph-v3-fast", "provider": "morph", "providerSlug": "morph", "name": "morph-v3-fast", "displayName": "morph-v3-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 16000, "maxInputTokens": 16000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "system_messages": true, "tool_choice": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "morph/morph-v3-fast", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "morph", "max_input_tokens": 16000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_vision": false } }, { "id": "morph/morph/morph-v3-large", "slug": "morph-morph-morph-v3-large", "provider": "morph", "providerSlug": "morph", "name": "morph-v3-large", "displayName": "morph-v3-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 1.9, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 0.0000019 } }, "limits": { "contextWindow": 16000, "maxInputTokens": 16000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "system_messages": true, "tool_choice": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "morph/morph-v3-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "morph", "max_input_tokens": 16000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 0.0000019, "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_vision": false } }, { "id": "vertex_ai-embedding-models/multimodalembedding", "slug": "vertex_ai-embedding-models-multimodalembedding", "provider": "vertex_ai-embedding-models", "providerSlug": "vertex_ai-embedding-models", "name": "multimodalembedding", "displayName": "multimodalembedding", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 100, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 2e-7, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 2e-7, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-7, "input_cost_per_video_per_second": 0.0005, "input_cost_per_video_per_second_above_15s_interval": 0.002, "input_cost_per_video_per_second_above_8s_interval": 0.001, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": null, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 768, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image", "video" ], "input": [], "output": [] }, "endpoints": [ "/v1/embeddings" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "multimodalembedding", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "rawLitellm": { "input_cost_per_character": 2e-7, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-7, "input_cost_per_video_per_second": 0.0005, "input_cost_per_video_per_second_above_15s_interval": 0.002, "input_cost_per_video_per_second_above_8s_interval": 0.001, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image", "video" ] } }, { "id": "vertex_ai-embedding-models/multimodalembedding@001", "slug": "vertex_ai-embedding-models-multimodalembedding-001", "provider": "vertex_ai-embedding-models", "providerSlug": "vertex_ai-embedding-models", "name": "multimodalembedding@001", "displayName": "multimodalembedding@001", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 100, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 2e-7, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 2e-7, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-7, "input_cost_per_video_per_second": 0.0005, "input_cost_per_video_per_second_above_15s_interval": 0.002, "input_cost_per_video_per_second_above_8s_interval": 0.001, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": null, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 768, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image", "video" ], "input": [], "output": [] }, "endpoints": [ "/v1/embeddings" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "multimodalembedding@001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "rawLitellm": { "input_cost_per_character": 2e-7, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-7, "input_cost_per_video_per_second": 0.0005, "input_cost_per_video_per_second_above_15s_interval": 0.002, "input_cost_per_video_per_second_above_8s_interval": 0.001, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image", "video" ] } }, { "id": "nscale/nscale/Qwen/QwQ-32B", "slug": "nscale-nscale-qwen-qwq-32b", "provider": "nscale", "providerSlug": "nscale", "name": "QwQ-32B", "displayName": "QwQ-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/Qwen/QwQ-32B", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 1.8e-7, "litellm_provider": "nscale", "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" } }, { "id": "nscale/nscale/Qwen/Qwen2.5-Coder-32B-Instruct", "slug": "nscale-nscale-qwen-qwen2-5-coder-32b-instruct", "provider": "nscale", "providerSlug": "nscale", "name": "Qwen2.5-Coder-32B-Instruct", "displayName": "Qwen2.5-Coder-32B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/Qwen/Qwen2.5-Coder-32B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "nscale", "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_aiderpolyglot_percentcorrect_qwen25coder32binstruct_benchmarkleaderboard_247": { "label": "Aider Polyglot", "category": "agentic", "score": 16.4, "scoreText": "16.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-Coder", "exactModelOrSnapshot": "Qwen2.5-Coder-32B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the 32B instruct checkpoint." } } }, { "id": "nscale/nscale/Qwen/Qwen2.5-Coder-3B-Instruct", "slug": "nscale-nscale-qwen-qwen2-5-coder-3b-instruct", "provider": "nscale", "providerSlug": "nscale", "name": "Qwen2.5-Coder-3B-Instruct", "displayName": "Qwen2.5-Coder-3B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.01, "outputUsdPer1MTokens": 0.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.01, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-8, "output_cost_per_token": 3e-8 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/Qwen/Qwen2.5-Coder-3B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 1e-8, "litellm_provider": "nscale", "mode": "chat", "output_cost_per_token": 3e-8, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_aiderpolyglot_percentcorrect_qwen25coder32binstruct_benchmarkleaderboard_247": { "label": "Aider Polyglot", "category": "agentic", "score": 16.4, "scoreText": "16.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-Coder", "exactModelOrSnapshot": "Qwen2.5-Coder-32B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the 32B instruct checkpoint." } } }, { "id": "nscale/nscale/Qwen/Qwen2.5-Coder-7B-Instruct", "slug": "nscale-nscale-qwen-qwen2-5-coder-7b-instruct", "provider": "nscale", "providerSlug": "nscale", "name": "Qwen2.5-Coder-7B-Instruct", "displayName": "Qwen2.5-Coder-7B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.01, "outputUsdPer1MTokens": 0.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.01, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-8, "output_cost_per_token": 3e-8 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/Qwen/Qwen2.5-Coder-7B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 1e-8, "litellm_provider": "nscale", "mode": "chat", "output_cost_per_token": 3e-8, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_aiderpolyglot_percentcorrect_qwen25coder32binstruct_benchmarkleaderboard_247": { "label": "Aider Polyglot", "category": "agentic", "score": 16.4, "scoreText": "16.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-Coder", "exactModelOrSnapshot": "Qwen2.5-Coder-32B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the 32B instruct checkpoint." } } }, { "id": "nscale/nscale/black-forest-labs/FLUX.1-schnell", "slug": "nscale-nscale-black-forest-labs-flux-1-schnell", "provider": "nscale", "providerSlug": "nscale", "name": "FLUX.1-schnell", "displayName": "FLUX.1-schnell", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 1.3e-9, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 1.3e-9, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/black-forest-labs/FLUX.1-schnell", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models" }, "rawLitellm": { "input_cost_per_pixel": 1.3e-9, "litellm_provider": "nscale", "mode": "image_generation", "output_cost_per_pixel": 0, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "nscale/nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "slug": "nscale-nscale-deepseek-ai-deepseek-r1-distill-llama-70b", "provider": "nscale", "providerSlug": "nscale", "name": "DeepSeek-R1-Distill-Llama-70B", "displayName": "DeepSeek-R1-Distill-Llama-70B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.375, "outputUsdPer1MTokens": 0.375, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.375, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.75e-7, "output_cost_per_token": 3.75e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 3.75e-7, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 3.75e-7, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "nscale/nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "slug": "nscale-nscale-deepseek-ai-deepseek-r1-distill-llama-8b", "provider": "nscale", "providerSlug": "nscale", "name": "DeepSeek-R1-Distill-Llama-8B", "displayName": "DeepSeek-R1-Distill-Llama-8B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.024999999999999998, "outputUsdPer1MTokens": 0.024999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.024999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-8, "output_cost_per_token": 2.5e-8 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 2.5e-8, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 2.5e-8, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "nscale/nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "slug": "nscale-nscale-deepseek-ai-deepseek-r1-distill-qwen-1-5b", "provider": "nscale", "providerSlug": "nscale", "name": "DeepSeek-R1-Distill-Qwen-1.5B", "displayName": "DeepSeek-R1-Distill-Qwen-1.5B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.09, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 9e-8 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 9e-8, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 9e-8, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "nscale/nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "slug": "nscale-nscale-deepseek-ai-deepseek-r1-distill-qwen-14b", "provider": "nscale", "providerSlug": "nscale", "name": "DeepSeek-R1-Distill-Qwen-14B", "displayName": "DeepSeek-R1-Distill-Qwen-14B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.07, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 7e-8 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 7e-8, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 7e-8, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "nscale/nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "slug": "nscale-nscale-deepseek-ai-deepseek-r1-distill-qwen-32b", "provider": "nscale", "providerSlug": "nscale", "name": "DeepSeek-R1-Distill-Qwen-32B", "displayName": "DeepSeek-R1-Distill-Qwen-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 1.5e-7, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "nscale/nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "slug": "nscale-nscale-deepseek-ai-deepseek-r1-distill-qwen-7b", "provider": "nscale", "providerSlug": "nscale", "name": "DeepSeek-R1-Distill-Qwen-7B", "displayName": "DeepSeek-R1-Distill-Qwen-7B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "nscale/nscale/meta-llama/Llama-3.1-8B-Instruct", "slug": "nscale-nscale-meta-llama-llama-3-1-8b-instruct", "provider": "nscale", "providerSlug": "nscale", "name": "Llama-3.1-8B-Instruct", "displayName": "Llama-3.1-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.03, "outputUsdPer1MTokens": 0.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.03, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-8, "output_cost_per_token": 3e-8 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/meta-llama/Llama-3.1-8B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 3e-8, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 3e-8, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "nscale/nscale/meta-llama/Llama-3.3-70B-Instruct", "slug": "nscale-nscale-meta-llama-llama-3-3-70b-instruct", "provider": "nscale", "providerSlug": "nscale", "name": "Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/meta-llama/Llama-3.3-70B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "nscale/nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct", "slug": "nscale-nscale-meta-llama-llama-4-scout-17b-16e-instruct", "provider": "nscale", "providerSlug": "nscale", "name": "Llama-4-Scout-17B-16E-Instruct", "displayName": "Llama-4-Scout-17B-16E-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.29, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 2.9e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 9e-8, "litellm_provider": "nscale", "mode": "chat", "output_cost_per_token": 2.9e-7, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "nscale/nscale/mistralai/mixtral-8x22b-instruct-v0.1", "slug": "nscale-nscale-mistralai-mixtral-8x22b-instruct-v0-1", "provider": "nscale", "providerSlug": "nscale", "name": "mixtral-8x22b-instruct-v0.1", "displayName": "mixtral-8x22b-instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/mistralai/mixtral-8x22b-instruct-v0.1", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "benchmarks": { "gsm8kmaj8_8shot_mixtral8x22binstruct_officiallaunchpost_212": { "label": "GSM8K maj@8", "category": "math", "score": 90.8, "scoreText": "90.8%", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on GSM8K maj@8." }, "mathmaj4_4shot_mixtral8x22binstruct_officiallaunchpost_213": { "label": "Math maj@4", "category": "math", "score": 44.6, "scoreText": "44.6%", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on Math maj@4." } } }, { "id": "nscale/nscale/stabilityai/stable-diffusion-xl-base-1.0", "slug": "nscale-nscale-stabilityai-stable-diffusion-xl-base-1-0", "provider": "nscale", "providerSlug": "nscale", "name": "stable-diffusion-xl-base-1.0", "displayName": "stable-diffusion-xl-base-1.0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 3e-9, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 3e-9, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nscale/stabilityai/stable-diffusion-xl-base-1.0", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models" }, "rawLitellm": { "input_cost_per_pixel": 3e-9, "litellm_provider": "nscale", "mode": "image_generation", "output_cost_per_pixel": 0, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "nebius/nebius/deepseek-ai/DeepSeek-R1", "slug": "nebius-nebius-deepseek-ai-deepseek-r1", "provider": "nebius", "providerSlug": "nebius", "name": "DeepSeek-R1", "displayName": "DeepSeek-R1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/deepseek-ai/DeepSeek-R1", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "nebius/nebius/deepseek-ai/DeepSeek-R1-0528", "slug": "nebius-nebius-deepseek-ai-deepseek-r1-0528", "provider": "nebius", "providerSlug": "nebius", "name": "DeepSeek-R1-0528", "displayName": "DeepSeek-R1-0528", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 164000, "maxInputTokens": 164000, "maxOutputTokens": 164000, "maxTokens": 164000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/deepseek-ai/DeepSeek-R1-0528", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 164000, "max_input_tokens": 164000, "max_output_tokens": 164000, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "nebius/nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "slug": "nebius-nebius-deepseek-ai-deepseek-r1-distill-llama-70b", "provider": "nebius", "providerSlug": "nebius", "name": "DeepSeek-R1-Distill-Llama-70B", "displayName": "DeepSeek-R1-Distill-Llama-70B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7.5e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7.5e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "nebius/nebius/deepseek-ai/DeepSeek-V3", "slug": "nebius-nebius-deepseek-ai-deepseek-v3", "provider": "nebius", "providerSlug": "nebius", "name": "DeepSeek-V3", "displayName": "DeepSeek-V3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/deepseek-ai/DeepSeek-V3", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "nebius/nebius/deepseek-ai/DeepSeek-V3-0324", "slug": "nebius-nebius-deepseek-ai-deepseek-v3-0324", "provider": "nebius", "providerSlug": "nebius", "name": "DeepSeek-V3-0324", "displayName": "DeepSeek-V3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/deepseek-ai/DeepSeek-V3-0324", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "nebius/nebius/google/gemma-3-27b-it", "slug": "nebius-nebius-google-gemma-3-27b-it", "provider": "nebius", "providerSlug": "nebius", "name": "gemma-3-27b-it", "displayName": "gemma-3-27b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/google/gemma-3-27b-it", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-8, "output_cost_per_token": 2e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "nebius/nebius/meta-llama/Llama-3.3-70B-Instruct", "slug": "nebius-nebius-meta-llama-llama-3-3-70b-instruct", "provider": "nebius", "providerSlug": "nebius", "name": "Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/meta-llama/Llama-3.3-70B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "nebius/nebius/meta-llama/Llama-Guard-3-8B", "slug": "nebius-nebius-meta-llama-llama-guard-3-8b", "provider": "nebius", "providerSlug": "nebius", "name": "Llama-Guard-3-8B", "displayName": "Llama-Guard-3-8B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": 0.06, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 6e-8 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/meta-llama/Llama-Guard-3-8B", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-8, "output_cost_per_token": 6e-8, "litellm_provider": "nebius", "mode": "chat", "source": "https://nebius.com/prices-ai-studio" } }, { "id": "nebius/nebius/meta-llama/Meta-Llama-3.1-8B-Instruct", "slug": "nebius-nebius-meta-llama-meta-llama-3-1-8b-instruct", "provider": "nebius", "providerSlug": "nebius", "name": "Meta-Llama-3.1-8B-Instruct", "displayName": "Meta-Llama-3.1-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": 0.06, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 6e-8 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-8, "output_cost_per_token": 6e-8, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "nebius/nebius/meta-llama/Meta-Llama-3.1-70B-Instruct", "slug": "nebius-nebius-meta-llama-meta-llama-3-1-70b-instruct", "provider": "nebius", "providerSlug": "nebius", "name": "Meta-Llama-3.1-70B-Instruct", "displayName": "Meta-Llama-3.1-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "nebius/nebius/meta-llama/Meta-Llama-3.1-405B-Instruct", "slug": "nebius-nebius-meta-llama-meta-llama-3-1-405b-instruct", "provider": "nebius", "providerSlug": "nebius", "name": "Meta-Llama-3.1-405B-Instruct", "displayName": "Meta-Llama-3.1-405B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "nebius/nebius/mistralai/Mistral-Nemo-Instruct-2407", "slug": "nebius-nebius-mistralai-mistral-nemo-instruct-2407", "provider": "nebius", "providerSlug": "nebius", "name": "Mistral-Nemo-Instruct-2407", "displayName": "Mistral-Nemo-Instruct-2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 1.2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/mistralai/Mistral-Nemo-Instruct-2407", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 4e-8, "output_cost_per_token": 1.2e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "nebius/nebius/NousResearch/Hermes-3-Llama-3.1-405B", "slug": "nebius-nebius-nousresearch-hermes-3-llama-3-1-405b", "provider": "nebius", "providerSlug": "nebius", "name": "Hermes-3-Llama-3.1-405B", "displayName": "Hermes-3-Llama-3.1-405B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/NousResearch/Hermes-3-Llama-3.1-405B", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "nebius/nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1", "slug": "nebius-nebius-nvidia-llama-3-1-nemotron-ultra-253b-v1", "provider": "nebius", "providerSlug": "nebius", "name": "Llama-3.1-Nemotron-Ultra-253B-v1", "displayName": "Llama-3.1-Nemotron-Ultra-253B-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "nebius/nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1", "slug": "nebius-nebius-nvidia-llama-3-3-nemotron-super-49b-v1", "provider": "nebius", "providerSlug": "nebius", "name": "Llama-3.3-Nemotron-Super-49B-v1", "displayName": "Llama-3.3-Nemotron-Super-49B-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "nebius/nebius/Qwen/Qwen3-235B-A22B", "slug": "nebius-nebius-qwen-qwen3-235b-a22b", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen3-235B-A22B", "displayName": "Qwen3-235B-A22B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen3-235B-A22B", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" } }, { "id": "nebius/nebius/Qwen/Qwen3-32B", "slug": "nebius-nebius-qwen-qwen3-32b", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen3-32B", "displayName": "Qwen3-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen3-32B", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" } }, { "id": "nebius/nebius/Qwen/Qwen3-30B-A3B", "slug": "nebius-nebius-qwen-qwen3-30b-a3b", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen3-30B-A3B", "displayName": "Qwen3-30B-A3B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen3-30B-A3B", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" } }, { "id": "nebius/nebius/Qwen/Qwen3-14B", "slug": "nebius-nebius-qwen-qwen3-14b", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen3-14B", "displayName": "Qwen3-14B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 2.4e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen3-14B", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 8e-8, "output_cost_per_token": 2.4e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" } }, { "id": "nebius/nebius/Qwen/Qwen3-4B", "slug": "nebius-nebius-qwen-qwen3-4b", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen3-4B", "displayName": "Qwen3-4B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 2.4e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen3-4B", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 8e-8, "output_cost_per_token": 2.4e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" } }, { "id": "nebius/nebius/Qwen/QwQ-32B", "slug": "nebius-nebius-qwen-qwq-32b", "provider": "nebius", "providerSlug": "nebius", "name": "QwQ-32B", "displayName": "QwQ-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.44999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 4.5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/QwQ-32B", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 4.5e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://nebius.com/prices-ai-studio" } }, { "id": "nebius/nebius/Qwen/Qwen2.5-72B-Instruct", "slug": "nebius-nebius-qwen-qwen2-5-72b-instruct", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen2.5-72B-Instruct", "displayName": "Qwen2.5-72B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen2.5-72B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." } } }, { "id": "nebius/nebius/Qwen/Qwen2.5-32B-Instruct", "slug": "nebius-nebius-qwen-qwen2-5-32b-instruct", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen2.5-32B-Instruct", "displayName": "Qwen2.5-32B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen2.5-32B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-8, "output_cost_per_token": 2e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." } } }, { "id": "nebius/nebius/Qwen/Qwen2.5-Coder-7B", "slug": "nebius-nebius-qwen-qwen2-5-coder-7b", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen2.5-Coder-7B", "displayName": "Qwen2.5-Coder-7B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.01, "outputUsdPer1MTokens": 0.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.01, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-8, "output_cost_per_token": 3e-8 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen2.5-Coder-7B", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-8, "output_cost_per_token": 3e-8, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_aiderpolyglot_percentcorrect_qwen25coder32binstruct_benchmarkleaderboard_247": { "label": "Aider Polyglot", "category": "agentic", "score": 16.4, "scoreText": "16.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-Coder", "exactModelOrSnapshot": "Qwen2.5-Coder-32B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the 32B instruct checkpoint." } } }, { "id": "nebius/nebius/Qwen/Qwen2.5-VL-72B-Instruct", "slug": "nebius-nebius-qwen-qwen2-5-vl-72b-instruct", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen2.5-VL-72B-Instruct", "displayName": "Qwen2.5-VL-72B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen2.5-VL-72B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_mmmu_score_qwen25vl32b_officialmodelcard_374": { "label": "MMMU", "category": "multimodal", "score": 70, "scoreText": "70", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mmmupro_score_qwen25vl32b_officialmodelcard_375": { "label": "MMMU-Pro", "category": "multimodal", "score": 49.5, "scoreText": "49.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mmstar_score_qwen25vl32b_officialmodelcard_376": { "label": "MMStar", "category": "multimodal", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mathvista_score_qwen25vl32b_officialmodelcard_377": { "label": "MathVista", "category": "multimodal", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mathvision_score_qwen25vl32b_officialmodelcard_378": { "label": "MathVision", "category": "multimodal", "score": 40, "scoreText": "40.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_ccocr_score_qwen25vl32b_officialmodelcard_379": { "label": "CC-OCR", "category": "multimodal", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_docvqa_score_qwen25vl32b_officialmodelcard_380": { "label": "DocVQA", "category": "multimodal", "score": 94.8, "scoreText": "94.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_infovqa_score_qwen25vl32b_officialmodelcard_381": { "label": "InfoVQA", "category": "multimodal", "score": 83.4, "scoreText": "83.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." } } }, { "id": "nebius/nebius/Qwen/Qwen2-VL-72B-Instruct", "slug": "nebius-nebius-qwen-qwen2-vl-72b-instruct", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen2-VL-72B-Instruct", "displayName": "Qwen2-VL-72B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen2-VL-72B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "local_mmmuval_score_qwen2vl7b_officialmodelcard_364": { "label": "MMMU", "category": "multimodal", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table compares Qwen2-VL-7B against InternVL2-8B, MiniCPM-V 2.6, and GPT-4o-mini." }, "local_docvqatest_score_qwen2vl7b_officialmodelcard_365": { "label": "DocVQA", "category": "multimodal", "score": 94.5, "scoreText": "94.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_infovqatest_score_qwen2vl7b_officialmodelcard_366": { "label": "InfoVQA", "category": "multimodal", "score": 76.5, "scoreText": "76.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_chartqatest_score_qwen2vl7b_officialmodelcard_367": { "label": "ChartQA", "category": "multimodal", "score": 83, "scoreText": "83.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_textvqaval_score_qwen2vl7b_officialmodelcard_368": { "label": "TextVQA", "category": "multimodal", "score": 84.3, "scoreText": "84.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_ocrbench_score_qwen2vl7b_officialmodelcard_369": { "label": "OCRBench", "category": "multimodal", "score": 845, "scoreText": "845", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_realworldqa_score_qwen2vl7b_officialmodelcard_370": { "label": "RealWorldQA", "category": "multimodal", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmbenchentest_score_qwen2vl7b_officialmodelcard_371": { "label": "MMBench-EN", "category": "multimodal", "score": 83, "scoreText": "83.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmbenchcntest_score_qwen2vl7b_officialmodelcard_372": { "label": "MMBench-CN", "category": "multimodal", "score": 80.5, "scoreText": "80.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmtbenchtest_score_qwen2vl7b_officialmodelcard_373": { "label": "MMT-Bench", "category": "multimodal", "score": 63.7, "scoreText": "63.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." } } }, { "id": "nebius/nebius/Qwen/Qwen2-VL-7B-Instruct", "slug": "nebius-nebius-qwen-qwen2-vl-7b-instruct", "provider": "nebius", "providerSlug": "nebius", "name": "Qwen2-VL-7B-Instruct", "displayName": "Qwen2-VL-7B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": 0.06, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 6e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/Qwen/Qwen2-VL-7B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-8, "output_cost_per_token": 6e-8, "litellm_provider": "nebius", "mode": "chat", "supports_vision": true, "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "local_mmmuval_score_qwen2vl7b_officialmodelcard_364": { "label": "MMMU", "category": "multimodal", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table compares Qwen2-VL-7B against InternVL2-8B, MiniCPM-V 2.6, and GPT-4o-mini." }, "local_docvqatest_score_qwen2vl7b_officialmodelcard_365": { "label": "DocVQA", "category": "multimodal", "score": 94.5, "scoreText": "94.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_infovqatest_score_qwen2vl7b_officialmodelcard_366": { "label": "InfoVQA", "category": "multimodal", "score": 76.5, "scoreText": "76.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_chartqatest_score_qwen2vl7b_officialmodelcard_367": { "label": "ChartQA", "category": "multimodal", "score": 83, "scoreText": "83.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_textvqaval_score_qwen2vl7b_officialmodelcard_368": { "label": "TextVQA", "category": "multimodal", "score": 84.3, "scoreText": "84.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_ocrbench_score_qwen2vl7b_officialmodelcard_369": { "label": "OCRBench", "category": "multimodal", "score": 845, "scoreText": "845", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_realworldqa_score_qwen2vl7b_officialmodelcard_370": { "label": "RealWorldQA", "category": "multimodal", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmbenchentest_score_qwen2vl7b_officialmodelcard_371": { "label": "MMBench-EN", "category": "multimodal", "score": 83, "scoreText": "83.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmbenchcntest_score_qwen2vl7b_officialmodelcard_372": { "label": "MMBench-CN", "category": "multimodal", "score": 80.5, "scoreText": "80.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmtbenchtest_score_qwen2vl7b_officialmodelcard_373": { "label": "MMT-Bench", "category": "multimodal", "score": 63.7, "scoreText": "63.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." } } }, { "id": "nebius/nebius/BAAI/bge-en-icl", "slug": "nebius-nebius-baai-bge-en-icl", "provider": "nebius", "providerSlug": "nebius", "name": "bge-en-icl", "displayName": "bge-en-icl", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.01, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.01, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": null, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/BAAI/bge-en-icl", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "input_cost_per_token": 1e-8, "output_cost_per_token": 0, "litellm_provider": "nebius", "mode": "embedding", "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "nebius/nebius/BAAI/bge-multilingual-gemma2", "slug": "nebius-nebius-baai-bge-multilingual-gemma2", "provider": "nebius", "providerSlug": "nebius", "name": "bge-multilingual-gemma2", "displayName": "bge-multilingual-gemma2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.01, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.01, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/BAAI/bge-multilingual-gemma2", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 1e-8, "output_cost_per_token": 0, "litellm_provider": "nebius", "mode": "embedding", "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "mmlu_5shottop1_gemma2pt27b_officialmodelcard_189": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "hellaswag_10shot_gemma2pt27b_officialmodelcard_190": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "humaneval_pass1_gemma2pt27b_officialmodelcard_191": { "label": "HumanEval", "category": "coding", "score": 51.8, "scoreText": "51.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "gsm8k_5shotmaj1_gemma2pt27b_officialmodelcard_192": { "label": "GSM8K", "category": "math", "score": 74, "scoreText": "74.0", "metric": "5-shot, maj@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mmlu_5shottop1_gemmapt27b_officialmodelcard_23": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_hellaswag_10shot_gemmapt27b_officialmodelcard_24": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_arcc_25shot_gemmapt27b_officialmodelcard_25": { "label": "ARC-Challenge", "category": "reasoning", "score": 71.4, "scoreText": "71.4", "metric": "25-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_triviaqa_5shot_gemmapt27b_officialmodelcard_26": { "label": "TriviaQA", "category": "general_knowledge", "score": 83.7, "scoreText": "83.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_realtoxicity_average_gemma2it27b_officialmodelcard_27": { "label": "RealToxicity", "category": "safety", "score": 8.84, "scoreText": "8.84", "metric": "average", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." }, "local_truthfulqa_score_gemma2it27b_officialmodelcard_28": { "label": "TruthfulQA", "category": "safety", "score": 51.6, "scoreText": "51.60", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." } } }, { "id": "nebius/nebius/intfloat/e5-mistral-7b-instruct", "slug": "nebius-nebius-intfloat-e5-mistral-7b-instruct", "provider": "nebius", "providerSlug": "nebius", "name": "e5-mistral-7b-instruct", "displayName": "e5-mistral-7b-instruct", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.01, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.01, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": null, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nebius/intfloat/e5-mistral-7b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://nebius.com/prices-ai-studio" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "input_cost_per_token": 1e-8, "output_cost_per_token": 0, "litellm_provider": "nebius", "mode": "embedding", "source": "https://nebius.com/prices-ai-studio" }, "benchmarks": { "local_mgteretrievaltable_avg_me5base_paper_338": { "label": "mGTE retrieval table", "category": "long_context", "score": 53.5, "scoreText": "53.5", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "e5", "exactModelOrSnapshot": "mE5-base", "modelDeveloper": "intfloat", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_me5large_paper_339": { "label": "mGTE retrieval table", "category": "long_context", "score": 57.7, "scoreText": "57.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "e5", "exactModelOrSnapshot": "mE5-large", "modelDeveloper": "intfloat", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_e5mistral7b_paper_340": { "label": "mGTE retrieval table", "category": "long_context", "score": 62.4, "scoreText": "62.4", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "e5", "exactModelOrSnapshot": "E5-mistral-7b", "modelDeveloper": "intfloat", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mrtydi_avgmrr10_multilinguale5small_officialmodelcard_347": { "label": "Mr. TyDi", "category": "other", "score": 64.4, "scoreText": "64.4", "metric": "Avg MRR@10", "higherIsBetter": true, "source_url": "https://huggingface.co/intfloat/multilingual-e5-large", "checked_at": "2026-05-31", "baseModelFamily": "e5", "exactModelOrSnapshot": "multilingual-e5-small", "modelDeveloper": "intfloat", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows from the model-card benchmark table." }, "local_mrtydi_avgmrr10_multilinguale5base_officialmodelcard_348": { "label": "Mr. TyDi", "category": "other", "score": 65.9, "scoreText": "65.9", "metric": "Avg MRR@10", "higherIsBetter": true, "source_url": "https://huggingface.co/intfloat/multilingual-e5-large", "checked_at": "2026-05-31", "baseModelFamily": "e5", "exactModelOrSnapshot": "multilingual-e5-base", "modelDeveloper": "intfloat", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows from the model-card benchmark table." }, "local_mrtydi_avgmrr10_multilinguale5large_officialmodelcard_349": { "label": "Mr. TyDi", "category": "other", "score": 70.5, "scoreText": "70.5", "metric": "Avg MRR@10", "higherIsBetter": true, "source_url": "https://huggingface.co/intfloat/multilingual-e5-large", "checked_at": "2026-05-31", "baseModelFamily": "e5", "exactModelOrSnapshot": "multilingual-e5-large", "modelDeveloper": "intfloat", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows from the model-card benchmark table." }, "local_table3comparison_beir_e5mistral7bfulldata_paper_350": { "label": "Table 3 comparison", "category": "other", "score": 56.9, "scoreText": "56.9", "metric": "BEIR", "higherIsBetter": true, "source_url": "https://arxiv.org/pdf/2401.00368", "checked_at": "2026-05-31", "baseModelFamily": "e5", "exactModelOrSnapshot": "E5mistral-7b + full data", "modelDeveloper": "intfloat", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published comparison table; BEIR is nDCG@10 over 15 BEIR datasets." }, "local_table3comparison_mteb_e5mistral7bfulldata_paper_351": { "label": "Table 3 comparison", "category": "other", "score": 66.6, "scoreText": "66.6", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://arxiv.org/pdf/2401.00368", "checked_at": "2026-05-31", "baseModelFamily": "e5", "exactModelOrSnapshot": "E5mistral-7b + full data", "modelDeveloper": "intfloat", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published comparison table; MTEB is the English-subset average." }, "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "bedrock_converse/nvidia.nemotron-nano-12b-v2", "slug": "bedrock_converse-nvidia-nemotron-nano-12b-v2", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "nvidia.nemotron-nano-12b-v2", "displayName": "nvidia.nemotron-nano-12b-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nvidia.nemotron-nano-12b-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-7, "supports_system_messages": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html" ], "manual_model_modalities_note": "Bedrock Converse exact NVIDIA route id from official docs" }, "benchmarks": { "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "bedrock_converse/nvidia.nemotron-nano-9b-v2", "slug": "bedrock_converse-nvidia-nemotron-nano-9b-v2", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "nvidia.nemotron-nano-9b-v2", "displayName": "nvidia.nemotron-nano-9b-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.22999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2.3e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nvidia.nemotron-nano-9b-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.3e-7, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html" ], "manual_model_modalities_note": "Bedrock Converse exact NVIDIA route id from official docs" }, "benchmarks": { "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "bedrock_converse/nvidia.nemotron-nano-3-30b", "slug": "bedrock_converse-nvidia-nemotron-nano-3-30b", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "nvidia.nemotron-nano-3-30b", "displayName": "nvidia.nemotron-nano-3-30b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true, "native_structured_output": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nvidia.nemotron-nano-3-30b", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-7, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nemotron-nano-3-30b.html" ], "manual_model_modalities_note": "Bedrock Converse exact NVIDIA route id from official docs" }, "benchmarks": { "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "bedrock_converse/nvidia.nemotron-super-3-120b", "slug": "bedrock_converse-nvidia-nemotron-super-3-120b", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "nvidia.nemotron-super-3-120b", "displayName": "nvidia.nemotron-super-3-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.65, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6.5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 256000, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nvidia.nemotron-super-3-120b", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.5e-7, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nemotron-super-3-120b.html" ], "manual_model_modalities_note": "Bedrock Converse exact NVIDIA route id from official docs" }, "benchmarks": { "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "openai/o1", "slug": "openai-o1", "provider": "OpenAI", "providerSlug": "openai", "name": "o1", "displayName": "o1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": 7.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o1" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" } }, { "id": "openai/o1-2024-12-17", "slug": "openai-o1-2024-12-17", "provider": "OpenAI", "providerSlug": "openai", "name": "o1-2024-12-17", "displayName": "o1-2024-12-17", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": 7.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o1-2024-12-17", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o1" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" } }, { "id": "openai/o1-pro", "slug": "openai-o1-pro", "provider": "OpenAI", "providerSlug": "openai", "name": "o1-pro", "displayName": "o1-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 150, "outputUsdPer1MTokens": 600, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 150, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 75, "batchOutputUsdPer1MTokens": 300, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 0.000075, "output_cost_per_token": 0.0006, "output_cost_per_token_batches": 0.0003 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": false, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o1-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 0.000075, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.0006, "output_cost_per_token_batches": 0.0003, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o1-pro" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" } }, { "id": "openai/o1-pro-2025-03-19", "slug": "openai-o1-pro-2025-03-19", "provider": "OpenAI", "providerSlug": "openai", "name": "o1-pro-2025-03-19", "displayName": "o1-pro-2025-03-19", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 150, "outputUsdPer1MTokens": 600, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 150, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 75, "batchOutputUsdPer1MTokens": 300, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 0.000075, "output_cost_per_token": 0.0006, "output_cost_per_token_batches": 0.0003 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": false, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o1-pro-2025-03-19", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 0.000075, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.0006, "output_cost_per_token_batches": 0.0003, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o1-pro" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" } }, { "id": "openai/o3", "slug": "openai-o3", "provider": "OpenAI", "providerSlug": "openai", "name": "o3", "displayName": "o3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 3.5, "priorityOutputUsdPer1MTokens": 14, "priorityCachedInputUsdPer1MTokens": 0.875, "flexInputUsdPer1MTokens": 1, "flexOutputUsdPer1MTokens": 4, "flexCachedInputUsdPer1MTokens": 0.25, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000035, "output_cost_per_token": 0.000008, "output_cost_per_token_flex": 0.000004, "output_cost_per_token_priority": 0.000014 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o3", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000008, "output_cost_per_token_flex": 0.000004, "output_cost_per_token_priority": 0.000014, "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o3" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "aime2025_accuracy_openaio3high_officiallaunchpost_12": { "label": "AIME 2025", "category": "reasoning", "score": 88.9, "scoreText": "88.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio3high_officiallaunchpost_13": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio3high_officiallaunchpost_14": { "label": "SWE-bench Verified", "category": "coding", "score": 69.1, "scoreText": "69.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "openai/o3-2025-04-16", "slug": "openai-o3-2025-04-16", "provider": "OpenAI", "providerSlug": "openai", "name": "o3-2025-04-16", "displayName": "o3-2025-04-16", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o3-2025-04-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000008, "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o3" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "aime2025_accuracy_openaio3high_officiallaunchpost_12": { "label": "AIME 2025", "category": "reasoning", "score": 88.9, "scoreText": "88.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio3high_officiallaunchpost_13": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio3high_officiallaunchpost_14": { "label": "SWE-bench Verified", "category": "coding", "score": 69.1, "scoreText": "69.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "openai/o3-deep-research", "slug": "openai-o3-deep-research", "provider": "OpenAI", "providerSlug": "openai", "name": "o3-deep-research", "displayName": "o3-deep-research", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 40, "cachedInputUsdPer1MTokens": 2.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 5, "batchOutputUsdPer1MTokens": 20, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_token": 0.00001, "input_cost_per_token_batches": 0.000005, "output_cost_per_token": 0.00004, "output_cost_per_token_batches": 0.00002 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o3-deep-research", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_token": 0.00001, "input_cost_per_token_batches": 0.000005, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.00004, "output_cost_per_token_batches": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "openai/o3-deep-research-2025-06-26", "slug": "openai-o3-deep-research-2025-06-26", "provider": "OpenAI", "providerSlug": "openai", "name": "o3-deep-research-2025-06-26", "displayName": "o3-deep-research-2025-06-26", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 40, "cachedInputUsdPer1MTokens": 2.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 5, "batchOutputUsdPer1MTokens": 20, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_token": 0.00001, "input_cost_per_token_batches": 0.000005, "output_cost_per_token": 0.00004, "output_cost_per_token_batches": 0.00002 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o3-deep-research-2025-06-26", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000025, "input_cost_per_token": 0.00001, "input_cost_per_token_batches": 0.000005, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.00004, "output_cost_per_token_batches": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "openai/o3-mini", "slug": "openai-o3-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "o3-mini", "displayName": "o3-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o3-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o3-mini" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "aime2024_accuracy_o3minihigh_officiallaunchpost_18": { "label": "AIME 2024", "category": "reasoning", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "gpqadiamond_accuracy_o3minihigh_officiallaunchpost_19": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 77, "scoreText": "77.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "swebenchverified_accuracy_o3minihigh_officiallaunchpost_20": { "label": "SWE-bench Verified", "category": "coding", "score": 48.9, "scoreText": "48.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; n=477 verified tasks." } } }, { "id": "openai/o3-mini-2025-01-31", "slug": "openai-o3-mini-2025-01-31", "provider": "OpenAI", "providerSlug": "openai", "name": "o3-mini-2025-01-31", "displayName": "o3-mini-2025-01-31", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o3-mini-2025-01-31", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o3-mini" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page" }, "benchmarks": { "aime2024_accuracy_o3minihigh_officiallaunchpost_18": { "label": "AIME 2024", "category": "reasoning", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "gpqadiamond_accuracy_o3minihigh_officiallaunchpost_19": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 77, "scoreText": "77.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "swebenchverified_accuracy_o3minihigh_officiallaunchpost_20": { "label": "SWE-bench Verified", "category": "coding", "score": 48.9, "scoreText": "48.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; n=477 verified tasks." } } }, { "id": "openai/o3-pro", "slug": "openai-o3-pro", "provider": "OpenAI", "providerSlug": "openai", "name": "o3-pro", "displayName": "o3-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 20, "outputUsdPer1MTokens": 80, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 20, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 10, "batchOutputUsdPer1MTokens": 40, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00002, "input_cost_per_token_batches": 0.00001, "output_cost_per_token": 0.00008, "output_cost_per_token_batches": 0.00004 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o3-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00002, "input_cost_per_token_batches": 0.00001, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.00008, "output_cost_per_token_batches": 0.00004, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o3-pro" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page" }, "benchmarks": { "gpqadiamond_accuracy_openaio3pro_benchmarkleaderboard_262": { "label": "GPQA Diamond", "category": "reasoning", "score": 84.5, "scoreText": "84.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/o3-pro/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "o3 Pro", "exactModelOrSnapshot": "openai/o3-pro", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. The page cites Artificial Analysis for the metric source." } } }, { "id": "openai/o3-pro-2025-06-10", "slug": "openai-o3-pro-2025-06-10", "provider": "OpenAI", "providerSlug": "openai", "name": "o3-pro-2025-06-10", "displayName": "o3-pro-2025-06-10", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 20, "outputUsdPer1MTokens": 80, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 20, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 10, "batchOutputUsdPer1MTokens": 40, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00002, "input_cost_per_token_batches": 0.00001, "output_cost_per_token": 0.00008, "output_cost_per_token_batches": 0.00004 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/responses", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o3-pro-2025-06-10", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00002, "input_cost_per_token_batches": 0.00001, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.00008, "output_cost_per_token_batches": 0.00004, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "gpqadiamond_accuracy_openaio3pro_benchmarkleaderboard_262": { "label": "GPQA Diamond", "category": "reasoning", "score": 84.5, "scoreText": "84.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/o3-pro/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "o3 Pro", "exactModelOrSnapshot": "openai/o3-pro", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. The page cites Artificial Analysis for the metric source." } } }, { "id": "openai/o4-mini", "slug": "openai-o4-mini", "provider": "OpenAI", "providerSlug": "openai", "name": "o4-mini", "displayName": "o4-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.275, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": 2, "priorityOutputUsdPer1MTokens": 8, "priorityCachedInputUsdPer1MTokens": 0.5, "flexInputUsdPer1MTokens": 0.55, "flexOutputUsdPer1MTokens": 2.2, "flexCachedInputUsdPer1MTokens": 0.1375, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.75e-7, "cache_read_input_token_cost_flex": 1.375e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token": 0.0000011, "input_cost_per_token_flex": 5.5e-7, "input_cost_per_token_priority": 0.000002, "output_cost_per_token": 0.0000044, "output_cost_per_token_flex": 0.0000022, "output_cost_per_token_priority": 0.000008 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "o4-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.75e-7, "cache_read_input_token_cost_flex": 1.375e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token": 0.0000011, "input_cost_per_token_flex": 5.5e-7, "input_cost_per_token_priority": 0.000002, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "output_cost_per_token_flex": 0.0000022, "output_cost_per_token_priority": 0.000008, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o4-mini" ], "manual_model_modalities_note": "OpenAI exact-model override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "aime2025_accuracy_openaio4minihigh_officiallaunchpost_15": { "label": "AIME 2025", "category": "reasoning", "score": 92.7, "scoreText": "92.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio4minihigh_officiallaunchpost_16": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 81.4, "scoreText": "81.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio4minihigh_officiallaunchpost_17": { "label": "SWE-bench Verified", "category": "coding", "score": 68.1, "scoreText": "68.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "openai/o4-mini-2025-04-16", "slug": "openai-o4-mini-2025-04-16", "provider": "OpenAI", "providerSlug": "openai", "name": "o4-mini-2025-04-16", "displayName": "o4-mini-2025-04-16", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.275, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.75e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": false, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "service_tier": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": "2026-04-22", "shutdownDate": "2026-10-23", "earliestShutdownDate": null, "sourceUrls": [ "https://developers.openai.com/api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "OpenAI docs explicitly list this snapshot under o4-mini." }, "source": { "type": "litellm", "litellmKey": "o4-mini-2025-04-16", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.75e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://developers.openai.com/api/docs/models/o4-mini" ], "manual_model_modalities_note": "OpenAI exact alias override from official model page", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://developers.openai.com/api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "OpenAI docs explicitly list this snapshot under o4-mini." }, "benchmarks": { "aime2025_accuracy_openaio4minihigh_officiallaunchpost_15": { "label": "AIME 2025", "category": "reasoning", "score": 92.7, "scoreText": "92.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio4minihigh_officiallaunchpost_16": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 81.4, "scoreText": "81.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio4minihigh_officiallaunchpost_17": { "label": "SWE-bench Verified", "category": "coding", "score": 68.1, "scoreText": "68.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "openai/o4-mini-deep-research", "slug": "openai-o4-mini-deep-research", "provider": "OpenAI", "providerSlug": "openai", "name": "o4-mini-deep-research", "displayName": "o4-mini-deep-research", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 4, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o4-mini-deep-research", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "aime2025_accuracy_openaio4minihigh_officiallaunchpost_15": { "label": "AIME 2025", "category": "reasoning", "score": 92.7, "scoreText": "92.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio4minihigh_officiallaunchpost_16": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 81.4, "scoreText": "81.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio4minihigh_officiallaunchpost_17": { "label": "SWE-bench Verified", "category": "coding", "score": 68.1, "scoreText": "68.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "openai/o4-mini-deep-research-2025-06-26", "slug": "openai-o4-mini-deep-research-2025-06-26", "provider": "OpenAI", "providerSlug": "openai", "name": "o4-mini-deep-research-2025-06-26", "displayName": "o4-mini-deep-research-2025-06-26", "mode": "responses", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 4, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "native_streaming": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "o4-mini-deep-research-2025-06-26", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.000008, "output_cost_per_token_batches": 0.000004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_modalities_contract_id": "responses_openai_azure_vision_text", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "aime2025_accuracy_openaio4minihigh_officiallaunchpost_15": { "label": "AIME 2025", "category": "reasoning", "score": 92.7, "scoreText": "92.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio4minihigh_officiallaunchpost_16": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 81.4, "scoreText": "81.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio4minihigh_officiallaunchpost_17": { "label": "SWE-bench Verified", "category": "coding", "score": 68.1, "scoreText": "68.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "oci/oci/meta.llama-3.1-405b-instruct", "slug": "oci-oci-meta-llama-3-1-405b-instruct", "provider": "oci", "providerSlug": "oci", "name": "meta.llama-3.1-405b-instruct", "displayName": "meta.llama-3.1-405b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10.68, "outputUsdPer1MTokens": 10.68, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10.68, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001068, "output_cost_per_token": 0.00001068 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/meta.llama-3.1-405b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.00001068, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.00001068, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "oci/oci/meta.llama-3.2-90b-vision-instruct", "slug": "oci-oci-meta-llama-3-2-90b-vision-instruct", "provider": "oci", "providerSlug": "oci", "name": "meta.llama-3.2-90b-vision-instruct", "displayName": "meta.llama-3.2-90b-vision-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/meta.llama-3.2-90b-vision-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "oci/oci/meta.llama-3.3-70b-instruct", "slug": "oci-oci-meta-llama-3-3-70b-instruct", "provider": "oci", "providerSlug": "oci", "name": "meta.llama-3.3-70b-instruct", "displayName": "meta.llama-3.3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/meta.llama-3.3-70b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-7, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "oci/oci/meta.llama-4-maverick-17b-128e-instruct-fp8", "slug": "oci-oci-meta-llama-4-maverick-17b-128e-instruct-fp8", "provider": "oci", "providerSlug": "oci", "name": "meta.llama-4-maverick-17b-128e-instruct-fp8", "displayName": "meta.llama-4-maverick-17b-128e-instruct-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 512000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/meta.llama-4-maverick-17b-128e-instruct-fp8", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "oci", "max_input_tokens": 512000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-7, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "oci/oci/meta.llama-4-scout-17b-16e-instruct", "slug": "oci-oci-meta-llama-4-scout-17b-16e-instruct", "provider": "oci", "providerSlug": "oci", "name": "meta.llama-4-scout-17b-16e-instruct", "displayName": "meta.llama-4-scout-17b-16e-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 192000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/meta.llama-4-scout-17b-16e-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "oci", "max_input_tokens": 192000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-7, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "oci/oci/xai.grok-3", "slug": "oci-oci-xai-grok-3", "provider": "oci", "providerSlug": "oci", "name": "xai.grok-3", "displayName": "xai.grok-3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/xai.grok-3", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "oci/oci/xai.grok-3-fast", "slug": "oci-oci-xai-grok-3-fast", "provider": "oci", "providerSlug": "oci", "name": "xai.grok-3-fast", "displayName": "xai.grok-3-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/xai.grok-3-fast", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000025, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "oci/oci/xai.grok-3-mini", "slug": "oci-oci-xai-grok-3-mini", "provider": "oci", "providerSlug": "oci", "name": "xai.grok-3-mini", "displayName": "xai.grok-3-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/xai.grok-3-mini", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-7, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "oci/oci/xai.grok-3-mini-fast", "slug": "oci-oci-xai-grok-3-mini-fast", "provider": "oci", "providerSlug": "oci", "name": "xai.grok-3-mini-fast", "displayName": "xai.grok-3-mini-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/xai.grok-3-mini-fast", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000004, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "oci/oci/xai.grok-4", "slug": "oci-oci-xai-grok-4", "provider": "oci", "providerSlug": "oci", "name": "xai.grok-4", "displayName": "xai.grok-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/xai.grok-4", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "oci/oci/cohere.command-latest", "slug": "oci-oci-cohere-command-latest", "provider": "oci", "providerSlug": "oci", "name": "cohere.command-latest", "displayName": "cohere.command-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.56, "outputUsdPer1MTokens": 1.56, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.56, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.command-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/cloud/ai/generative-ai/pricing/" }, "rawLitellm": { "input_cost_per_token": 0.00000156, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.00000156, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_function_calling": true, "supports_response_schema": false } }, { "id": "oci/oci/cohere.command-a-03-2025", "slug": "oci-oci-cohere-command-a-03-2025", "provider": "oci", "providerSlug": "oci", "name": "cohere.command-a-03-2025", "displayName": "cohere.command-a-03-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.56, "outputUsdPer1MTokens": 1.56, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.56, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 256000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.command-a-03-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/cloud/ai/generative-ai/pricing/" }, "rawLitellm": { "input_cost_per_token": 0.00000156, "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.00000156, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "mmlu_accuracy_commanda_paper_130": { "label": "MMLU", "category": "general_knowledge", "score": 85.5, "scoreText": "85.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "mmlupro_accuracy_commanda_paper_131": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "gpqa_accuracy_commanda_paper_132": { "label": "GPQA", "category": "general_knowledge", "score": 50.8, "scoreText": "50.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "ifeval_strictaccuracy_commanda_paper_133": { "label": "IFEval", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "strict accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; instruction-following benchmark for Command A." }, "bfcloverall_score_commanda_paper_134": { "label": "BFCL", "category": "agentic", "score": 63.8, "scoreText": "63.8", "metric": "score", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 5 in the official technical report; BFCL values are taken from the official leaderboard." }, "taubenchretail_pass1_commanda_paper_135": { "label": "Taubench Retail", "category": "agentic", "score": 60, "scoreText": "P@1 60.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." }, "taubenchairline_pass1_commanda_paper_136": { "label": "Taubench Airline", "category": "agentic", "score": 45.3, "scoreText": "P@1 45.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." } } }, { "id": "oci/oci/cohere.command-plus-latest", "slug": "oci-oci-cohere-command-plus-latest", "provider": "oci", "providerSlug": "oci", "name": "cohere.command-plus-latest", "displayName": "cohere.command-plus-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.56, "outputUsdPer1MTokens": 1.56, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.56, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.command-plus-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/cloud/ai/generative-ai/pricing/" }, "rawLitellm": { "input_cost_per_token": 0.00000156, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.00000156, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_function_calling": true, "supports_response_schema": false } }, { "id": "oci/oci/cohere.command-a-reasoning-08-2025", "slug": "oci-oci-cohere-command-a-reasoning-08-2025", "provider": "oci", "providerSlug": "oci", "name": "cohere.command-a-reasoning-08-2025", "displayName": "cohere.command-a-reasoning-08-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.56, "outputUsdPer1MTokens": 1.56, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.56, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 256000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.command-a-reasoning-08-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.00000156, "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.00000156, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "mmlu_accuracy_commanda_paper_130": { "label": "MMLU", "category": "general_knowledge", "score": 85.5, "scoreText": "85.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "mmlupro_accuracy_commanda_paper_131": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "gpqa_accuracy_commanda_paper_132": { "label": "GPQA", "category": "general_knowledge", "score": 50.8, "scoreText": "50.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "ifeval_strictaccuracy_commanda_paper_133": { "label": "IFEval", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "strict accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; instruction-following benchmark for Command A." }, "bfcloverall_score_commanda_paper_134": { "label": "BFCL", "category": "agentic", "score": 63.8, "scoreText": "63.8", "metric": "score", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 5 in the official technical report; BFCL values are taken from the official leaderboard." }, "taubenchretail_pass1_commanda_paper_135": { "label": "Taubench Retail", "category": "agentic", "score": 60, "scoreText": "P@1 60.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." }, "taubenchairline_pass1_commanda_paper_136": { "label": "Taubench Airline", "category": "agentic", "score": 45.3, "scoreText": "P@1 45.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." } } }, { "id": "oci/oci/cohere.command-a-vision-07-2025", "slug": "oci-oci-cohere-command-a-vision-07-2025", "provider": "oci", "providerSlug": "oci", "name": "cohere.command-a-vision-07-2025", "displayName": "cohere.command-a-vision-07-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.56, "outputUsdPer1MTokens": 1.56, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.56, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.command-a-vision-07-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.00000156, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.00000156, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true }, "benchmarks": { "mmlu_accuracy_commanda_paper_130": { "label": "MMLU", "category": "general_knowledge", "score": 85.5, "scoreText": "85.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "mmlupro_accuracy_commanda_paper_131": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "gpqa_accuracy_commanda_paper_132": { "label": "GPQA", "category": "general_knowledge", "score": 50.8, "scoreText": "50.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "ifeval_strictaccuracy_commanda_paper_133": { "label": "IFEval", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "strict accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; instruction-following benchmark for Command A." }, "bfcloverall_score_commanda_paper_134": { "label": "BFCL", "category": "agentic", "score": 63.8, "scoreText": "63.8", "metric": "score", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 5 in the official technical report; BFCL values are taken from the official leaderboard." }, "taubenchretail_pass1_commanda_paper_135": { "label": "Taubench Retail", "category": "agentic", "score": 60, "scoreText": "P@1 60.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." }, "taubenchairline_pass1_commanda_paper_136": { "label": "Taubench Airline", "category": "agentic", "score": 45.3, "scoreText": "P@1 45.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." } } }, { "id": "oci/oci/cohere.command-a-translate-08-2025", "slug": "oci-oci-cohere-command-a-translate-08-2025", "provider": "oci", "providerSlug": "oci", "name": "cohere.command-a-translate-08-2025", "displayName": "cohere.command-a-translate-08-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.09, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 9e-8 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 256000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.command-a-translate-08-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 9e-8, "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-8, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": false, "supports_response_schema": false }, "benchmarks": { "mmlu_accuracy_commanda_paper_130": { "label": "MMLU", "category": "general_knowledge", "score": 85.5, "scoreText": "85.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "mmlupro_accuracy_commanda_paper_131": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "gpqa_accuracy_commanda_paper_132": { "label": "GPQA", "category": "general_knowledge", "score": 50.8, "scoreText": "50.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "ifeval_strictaccuracy_commanda_paper_133": { "label": "IFEval", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "strict accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; instruction-following benchmark for Command A." }, "bfcloverall_score_commanda_paper_134": { "label": "BFCL", "category": "agentic", "score": 63.8, "scoreText": "63.8", "metric": "score", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 5 in the official technical report; BFCL values are taken from the official leaderboard." }, "taubenchretail_pass1_commanda_paper_135": { "label": "Taubench Retail", "category": "agentic", "score": 60, "scoreText": "P@1 60.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." }, "taubenchairline_pass1_commanda_paper_136": { "label": "Taubench Airline", "category": "agentic", "score": 45.3, "scoreText": "P@1 45.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." } } }, { "id": "oci/oci/cohere.command-r-08-2024", "slug": "oci-oci-cohere-command-r-08-2024", "provider": "oci", "providerSlug": "oci", "name": "cohere.command-r-08-2024", "displayName": "cohere.command-r-08-2024", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.command-r-08-2024", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-7, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false } }, { "id": "oci/oci/cohere.command-r-plus-08-2024", "slug": "oci-oci-cohere-command-r-plus-08-2024", "provider": "oci", "providerSlug": "oci", "name": "cohere.command-r-plus-08-2024", "displayName": "cohere.command-r-plus-08-2024", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.56, "outputUsdPer1MTokens": 1.56, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.56, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.command-r-plus-08-2024", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.00000156, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.00000156, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false } }, { "id": "oci/oci/meta.llama-3.2-11b-vision-instruct", "slug": "oci-oci-meta-llama-3-2-11b-vision-instruct", "provider": "oci", "providerSlug": "oci", "name": "meta.llama-3.2-11b-vision-instruct", "displayName": "meta.llama-3.2-11b-vision-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/meta.llama-3.2-11b-vision-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "oci/oci/meta.llama-3.1-70b-instruct", "slug": "oci-oci-meta-llama-3-1-70b-instruct", "provider": "oci", "providerSlug": "oci", "name": "meta.llama-3.1-70b-instruct", "displayName": "meta.llama-3.1-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/meta.llama-3.1-70b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-7, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "oci/oci/meta.llama-3.3-70b-instruct-fp8-dynamic", "slug": "oci-oci-meta-llama-3-3-70b-instruct-fp8-dynamic", "provider": "oci", "providerSlug": "oci", "name": "meta.llama-3.3-70b-instruct-fp8-dynamic", "displayName": "meta.llama-3.3-70b-instruct-fp8-dynamic", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/meta.llama-3.3-70b-instruct-fp8-dynamic", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-7, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "oci/oci/xai.grok-4-fast", "slug": "oci-oci-xai-grok-4-fast", "provider": "oci", "providerSlug": "oci", "name": "xai.grok-4-fast", "displayName": "xai.grok-4-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/xai.grok-4-fast", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000025, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "oci/oci/xai.grok-4.1-fast", "slug": "oci-oci-xai-grok-4-1-fast", "provider": "oci", "providerSlug": "oci", "name": "xai.grok-4.1-fast", "displayName": "xai.grok-4.1-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/xai.grok-4.1-fast", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000025, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "oci/oci/xai.grok-4.20", "slug": "oci-oci-xai-grok-4-20", "provider": "oci", "providerSlug": "oci", "name": "xai.grok-4.20", "displayName": "xai.grok-4.20", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/xai.grok-4.20", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "oci/oci/xai.grok-4.20-multi-agent", "slug": "oci-oci-xai-grok-4-20-multi-agent", "provider": "oci", "providerSlug": "oci", "name": "xai.grok-4.20-multi-agent", "displayName": "xai.grok-4.20-multi-agent", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/xai.grok-4.20-multi-agent", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "oci/oci/xai.grok-code-fast-1", "slug": "oci-oci-xai-grok-code-fast-1", "provider": "oci", "providerSlug": "oci", "name": "xai.grok-code-fast-1", "displayName": "xai.grok-code-fast-1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/xai.grok-code-fast-1", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000025, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false } }, { "id": "oci/oci/google.gemini-2.5-pro", "slug": "oci-oci-google-gemini-2-5-pro", "provider": "oci", "providerSlug": "oci", "name": "google.gemini-2.5-pro", "displayName": "google.gemini-2.5-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/google.gemini-2.5-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 0.00000125, "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.00001, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "oci/oci/google.gemini-2.5-flash", "slug": "oci-oci-google-gemini-2-5-flash", "provider": "oci", "providerSlug": "oci", "name": "google.gemini-2.5-flash", "displayName": "google.gemini-2.5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/google.gemini-2.5-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true } }, { "id": "oci/oci/google.gemini-2.5-flash-lite", "slug": "oci-oci-google-gemini-2-5-flash-lite", "provider": "oci", "providerSlug": "oci", "name": "google.gemini-2.5-flash-lite", "displayName": "google.gemini-2.5-flash-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/google.gemini-2.5-flash-lite", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 7.5e-8, "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "benchmarks": { "humanityslastexam_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_90": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 7.3, "scoreText": "7.3% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "gpqadiamond_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_91": { "label": "GPQA Diamond", "category": "science", "score": 71.7, "scoreText": "71.7% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "aime2025_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_92": { "label": "AIME 2025", "category": "math", "score": 48.2, "scoreText": "48.2% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "livecodebenchv5_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_93": { "label": "LiveCodeBench v5", "category": "coding", "score": 58.4, "scoreText": "58.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "swebenchverified_accuracy_gemini25flashlitepreview092025thinking_officialmodelcard_94": { "label": "SWE-bench Verified", "category": "agentic", "score": 38.9, "scoreText": "38.9% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." }, "mmmu_pass1_gemini25flashlitepreview092025thinking_officialmodelcard_95": { "label": "MMMU", "category": "multimodal", "score": 72, "scoreText": "72.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.5 Flash-Lite Preview (09-2025) Thinking", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Selected from the 09-2025 Thinking column in the September 2025 model card update." } } }, { "id": "oci/oci/cohere.embed-english-v3.0", "slug": "oci-oci-cohere-embed-english-v3-0", "provider": "oci", "providerSlug": "oci", "name": "cohere.embed-english-v3.0", "displayName": "cohere.embed-english-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.embed-english-v3.0", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "oci", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } }, { "id": "oci/oci/cohere.embed-english-light-v3.0", "slug": "oci-oci-cohere-embed-english-light-v3-0", "provider": "oci", "providerSlug": "oci", "name": "cohere.embed-english-light-v3.0", "displayName": "cohere.embed-english-light-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 384, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.embed-english-light-v3.0", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "oci", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } }, { "id": "oci/oci/cohere.embed-multilingual-v3.0", "slug": "oci-oci-cohere-embed-multilingual-v3-0", "provider": "oci", "providerSlug": "oci", "name": "cohere.embed-multilingual-v3.0", "displayName": "cohere.embed-multilingual-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.embed-multilingual-v3.0", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "oci", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } }, { "id": "oci/oci/cohere.embed-multilingual-light-v3.0", "slug": "oci-oci-cohere-embed-multilingual-light-v3-0", "provider": "oci", "providerSlug": "oci", "name": "cohere.embed-multilingual-light-v3.0", "displayName": "cohere.embed-multilingual-light-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 384, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.embed-multilingual-light-v3.0", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "oci", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" } }, { "id": "oci/oci/cohere.embed-english-image-v3.0", "slug": "oci-oci-cohere-embed-english-image-v3-0", "provider": "oci", "providerSlug": "oci", "name": "cohere.embed-english-image-v3.0", "displayName": "cohere.embed-english-image-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.embed-english-image-v3.0", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "oci", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true } }, { "id": "oci/oci/cohere.embed-english-light-image-v3.0", "slug": "oci-oci-cohere-embed-english-light-image-v3-0", "provider": "oci", "providerSlug": "oci", "name": "cohere.embed-english-light-image-v3.0", "displayName": "cohere.embed-english-light-image-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 384, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.embed-english-light-image-v3.0", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "oci", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true } }, { "id": "oci/oci/cohere.embed-multilingual-light-image-v3.0", "slug": "oci-oci-cohere-embed-multilingual-light-image-v3-0", "provider": "oci", "providerSlug": "oci", "name": "cohere.embed-multilingual-light-image-v3.0", "displayName": "cohere.embed-multilingual-light-image-v3.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 384, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.embed-multilingual-light-image-v3.0", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "oci", "max_input_tokens": 512, "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true } }, { "id": "oci/oci/cohere.embed-v4.0", "slug": "oci-oci-cohere-embed-v4-0", "provider": "oci", "providerSlug": "oci", "name": "cohere.embed-v4.0", "displayName": "cohere.embed-v4.0", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1536, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "embedding_image_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "oci/cohere.embed-v4.0", "syncedAt": "2026-05-28", "sourceUrl": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "oci", "max_input_tokens": 128000, "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1536, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true } }, { "id": "ollama/ollama/codegeex4", "slug": "ollama-ollama-codegeex4", "provider": "ollama", "providerSlug": "ollama", "name": "codegeex4", "displayName": "codegeex4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/codegeex4", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": false } }, { "id": "ollama/ollama/codegemma", "slug": "ollama-ollama-codegemma", "provider": "ollama", "providerSlug": "ollama", "name": "codegemma", "displayName": "codegemma", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/codegemma", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0 }, "benchmarks": { "local_humanevalpython_score_codegemma2b_benchmarkleaderboard_43": { "label": "HumanEval", "category": "coding", "score": 27.28, "scoreText": "27.28", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-2B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the humaneval-python column for CodeGemma-2B." }, "local_javascript_score_codegemma2b_benchmarkleaderboard_44": { "label": "javascript", "category": "coding", "score": 29.94, "scoreText": "29.94", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-2B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the javascript column for CodeGemma-2B." }, "local_humanevalpython_score_codegemma7b_benchmarkleaderboard_45": { "label": "HumanEval", "category": "coding", "score": 40.13, "scoreText": "40.13", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the humaneval-python column for CodeGemma-7B." }, "local_javascript_score_codegemma7b_benchmarkleaderboard_46": { "label": "javascript", "category": "coding", "score": 43.06, "scoreText": "43.06", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the javascript column for CodeGemma-7B." }, "local_humanevalpython_score_codegemma7bit_benchmarkleaderboard_47": { "label": "HumanEval", "category": "coding", "score": 52.74, "scoreText": "52.74", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B-it", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the humaneval-python column for CodeGemma-7B-it." }, "local_javascript_score_codegemma7bit_benchmarkleaderboard_48": { "label": "javascript", "category": "coding", "score": 47.71, "scoreText": "47.71", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B-it", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the javascript column for CodeGemma-7B-it." }, "local_cpp_score_codegemma7bit_benchmarkleaderboard_49": { "label": "cpp", "category": "coding", "score": 42.6, "scoreText": "42.60", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B-it", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the cpp column for CodeGemma-7B-it." } } }, { "id": "ollama/ollama/codellama", "slug": "ollama-ollama-codellama", "provider": "ollama", "providerSlug": "ollama", "name": "codellama", "displayName": "codellama", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/codellama", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0 }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "ollama/ollama/deepseek-coder-v2-base", "slug": "ollama-ollama-deepseek-coder-v2-base", "provider": "ollama", "providerSlug": "ollama", "name": "deepseek-coder-v2-base", "displayName": "deepseek-coder-v2-base", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/deepseek-coder-v2-base", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "ollama/ollama/deepseek-coder-v2-instruct", "slug": "ollama-ollama-deepseek-coder-v2-instruct", "provider": "ollama", "providerSlug": "ollama", "name": "deepseek-coder-v2-instruct", "displayName": "deepseek-coder-v2-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/deepseek-coder-v2-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "ollama/ollama/deepseek-coder-v2-lite-base", "slug": "ollama-ollama-deepseek-coder-v2-lite-base", "provider": "ollama", "providerSlug": "ollama", "name": "deepseek-coder-v2-lite-base", "displayName": "deepseek-coder-v2-lite-base", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/deepseek-coder-v2-lite-base", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "ollama/ollama/deepseek-coder-v2-lite-instruct", "slug": "ollama-ollama-deepseek-coder-v2-lite-instruct", "provider": "ollama", "providerSlug": "ollama", "name": "deepseek-coder-v2-lite-instruct", "displayName": "deepseek-coder-v2-lite-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/deepseek-coder-v2-lite-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "ollama/ollama/deepseek-v3.1:671b-cloud", "slug": "ollama-ollama-deepseek-v3-1-671b-cloud", "provider": "ollama", "providerSlug": "ollama", "name": "deepseek-v3.1:671b-cloud", "displayName": "deepseek-v3.1:671b-cloud", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/deepseek-v3.1:671b-cloud", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "ollama/ollama/gpt-oss:120b-cloud", "slug": "ollama-ollama-gpt-oss-120b-cloud", "provider": "ollama", "providerSlug": "ollama", "name": "gpt-oss:120b-cloud", "displayName": "gpt-oss:120b-cloud", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/gpt-oss:120b-cloud", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "ollama/ollama/gpt-oss:20b-cloud", "slug": "ollama-ollama-gpt-oss-20b-cloud", "provider": "ollama", "providerSlug": "ollama", "name": "gpt-oss:20b-cloud", "displayName": "gpt-oss:20b-cloud", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/gpt-oss:20b-cloud", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "ollama/ollama/internlm2_5-20b-chat", "slug": "ollama-ollama-internlm2_5-20b-chat", "provider": "ollama", "providerSlug": "ollama", "name": "internlm2_5-20b-chat", "displayName": "internlm2_5-20b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/internlm2_5-20b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true } }, { "id": "ollama/ollama/llama2", "slug": "ollama-ollama-llama2", "provider": "ollama", "providerSlug": "ollama", "name": "llama2", "displayName": "llama2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/llama2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0 } }, { "id": "ollama/ollama/llama2-uncensored", "slug": "ollama-ollama-llama2-uncensored", "provider": "ollama", "providerSlug": "ollama", "name": "llama2-uncensored", "displayName": "llama2-uncensored", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/llama2-uncensored", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0 } }, { "id": "ollama/ollama/llama2:13b", "slug": "ollama-ollama-llama2-13b", "provider": "ollama", "providerSlug": "ollama", "name": "llama2:13b", "displayName": "llama2:13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/llama2:13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0 } }, { "id": "ollama/ollama/llama2:70b", "slug": "ollama-ollama-llama2-70b", "provider": "ollama", "providerSlug": "ollama", "name": "llama2:70b", "displayName": "llama2:70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/llama2:70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0 } }, { "id": "ollama/ollama/llama2:7b", "slug": "ollama-ollama-llama2-7b", "provider": "ollama", "providerSlug": "ollama", "name": "llama2:7b", "displayName": "llama2:7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/llama2:7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0 } }, { "id": "ollama/ollama/llama3", "slug": "ollama-ollama-llama3", "provider": "ollama", "providerSlug": "ollama", "name": "llama3", "displayName": "llama3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/llama3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0 } }, { "id": "ollama/ollama/llama3.1", "slug": "ollama-ollama-llama3-1", "provider": "ollama", "providerSlug": "ollama", "name": "llama3.1", "displayName": "llama3.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/llama3.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "ollama/ollama/llama3:70b", "slug": "ollama-ollama-llama3-70b", "provider": "ollama", "providerSlug": "ollama", "name": "llama3:70b", "displayName": "llama3:70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/llama3:70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0 } }, { "id": "ollama/ollama/llama3:8b", "slug": "ollama-ollama-llama3-8b", "provider": "ollama", "providerSlug": "ollama", "name": "llama3:8b", "displayName": "llama3:8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/llama3:8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0 } }, { "id": "ollama/ollama/mistral", "slug": "ollama-ollama-mistral", "provider": "ollama", "providerSlug": "ollama", "name": "mistral", "displayName": "mistral", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/mistral", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0, "supports_function_calling": true } }, { "id": "ollama/ollama/mistral-7B-Instruct-v0.1", "slug": "ollama-ollama-mistral-7b-instruct-v0-1", "provider": "ollama", "providerSlug": "ollama", "name": "mistral-7B-Instruct-v0.1", "displayName": "mistral-7B-Instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/mistral-7B-Instruct-v0.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "ollama/ollama/mistral-7B-Instruct-v0.2", "slug": "ollama-ollama-mistral-7b-instruct-v0-2", "provider": "ollama", "providerSlug": "ollama", "name": "mistral-7B-Instruct-v0.2", "displayName": "mistral-7B-Instruct-v0.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/mistral-7B-Instruct-v0.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "ollama/ollama/mistral-large-instruct-2407", "slug": "ollama-ollama-mistral-large-instruct-2407", "provider": "ollama", "providerSlug": "ollama", "name": "mistral-large-instruct-2407", "displayName": "mistral-large-instruct-2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65536, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/mistral-large-instruct-2407", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true } }, { "id": "ollama/ollama/mixtral-8x22B-Instruct-v0.1", "slug": "ollama-ollama-mixtral-8x22b-instruct-v0-1", "provider": "ollama", "providerSlug": "ollama", "name": "mixtral-8x22B-Instruct-v0.1", "displayName": "mixtral-8x22B-Instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/mixtral-8x22B-Instruct-v0.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "gsm8kmaj8_8shot_mixtral8x22binstruct_officiallaunchpost_212": { "label": "GSM8K maj@8", "category": "math", "score": 90.8, "scoreText": "90.8%", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on GSM8K maj@8." }, "mathmaj4_4shot_mixtral8x22binstruct_officiallaunchpost_213": { "label": "Math maj@4", "category": "math", "score": 44.6, "scoreText": "44.6%", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on Math maj@4." } } }, { "id": "ollama/ollama/mixtral-8x7B-Instruct-v0.1", "slug": "ollama-ollama-mixtral-8x7b-instruct-v0-1", "provider": "ollama", "providerSlug": "ollama", "name": "mixtral-8x7B-Instruct-v0.1", "displayName": "mixtral-8x7B-Instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/mixtral-8x7B-Instruct-v0.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true } }, { "id": "ollama/ollama/orca-mini", "slug": "ollama-ollama-orca-mini", "provider": "ollama", "providerSlug": "ollama", "name": "orca-mini", "displayName": "orca-mini", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/orca-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0 } }, { "id": "ollama/ollama/qwen3-coder:480b-cloud", "slug": "ollama-ollama-qwen3-coder-480b-cloud", "provider": "ollama", "providerSlug": "ollama", "name": "qwen3-coder:480b-cloud", "displayName": "qwen3-coder:480b-cloud", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/qwen3-coder:480b-cloud", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "ollama/ollama/vicuna", "slug": "ollama-ollama-vicuna", "provider": "ollama", "providerSlug": "ollama", "name": "vicuna", "displayName": "vicuna", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ollama/vicuna", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "ollama", "max_input_tokens": 2048, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "completion", "output_cost_per_token": 0 } }, { "id": "openai/omni-moderation-2024-09-26", "slug": "openai-omni-moderation-2024-09-26", "provider": "OpenAI", "providerSlug": "openai", "name": "omni-moderation-2024-09-26", "displayName": "omni-moderation-2024-09-26", "mode": "moderation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 32768, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "omni-moderation-2024-09-26", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0 } }, { "id": "openai/omni-moderation-latest", "slug": "openai-omni-moderation-latest", "provider": "OpenAI", "providerSlug": "openai", "name": "omni-moderation-latest", "displayName": "omni-moderation-latest", "mode": "moderation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 32768, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "omni-moderation-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0 } }, { "id": "bedrock_converse/openai.gpt-oss-120b-1:0", "slug": "bedrock_converse-openai-gpt-oss-120b-1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "openai.gpt-oss-120b-1:0", "displayName": "openai.gpt-oss-120b-1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openai.gpt-oss-120b-1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "bedrock_converse/openai.gpt-oss-20b-1:0", "slug": "bedrock_converse-openai-gpt-oss-20b-1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "openai.gpt-oss-20b-1:0", "displayName": "openai.gpt-oss-20b-1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openai.gpt-oss-20b-1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "bedrock_converse/openai.gpt-oss-safeguard-120b", "slug": "bedrock_converse-openai-gpt-oss-safeguard-120b", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "openai.gpt-oss-safeguard-120b", "displayName": "openai.gpt-oss-safeguard-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openai.gpt-oss-safeguard-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-7, "supports_system_messages": true }, "benchmarks": { "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "bedrock_converse/openai.gpt-oss-safeguard-20b", "slug": "bedrock_converse-openai-gpt-oss-safeguard-20b", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "openai.gpt-oss-safeguard-20b", "displayName": "openai.gpt-oss-safeguard-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openai.gpt-oss-safeguard-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-7, "supports_system_messages": true }, "benchmarks": { "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "openrouter/openrouter/anthropic/claude-3-haiku", "slug": "openrouter-openrouter-anthropic-claude-3-haiku", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-3-haiku", "displayName": "claude-3-haiku", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 400, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0004, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-3-haiku", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.0004, "input_cost_per_token": 2.5e-7, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "max_input_tokens": 200000, "max_output_tokens": 4096, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "Claude", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/anthropic/claude-3.5-sonnet", "slug": "openrouter-openrouter-anthropic-claude-3-5-sonnet", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-3.5-sonnet", "displayName": "claude-3.5-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-3.5-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "openrouter/openrouter/anthropic/claude-3.7-sonnet", "slug": "openrouter-openrouter-anthropic-claude-3-7-sonnet", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-3.7-sonnet", "displayName": "claude-3.7-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 4800, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0048, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-3.7-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.0048, "input_cost_per_token": 0.000003, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "openrouter/openrouter/anthropic/claude-opus-4", "slug": "openrouter-openrouter-anthropic-claude-opus-4", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-opus-4", "displayName": "claude-opus-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 4800, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "image", "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-opus-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "Claude", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "openrouter/openrouter/anthropic/claude-opus-4.1", "slug": "openrouter-openrouter-anthropic-claude-opus-4-1", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-opus-4.1", "displayName": "claude-opus-4.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 4800, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.00003, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "image", "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-opus-4.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 0.00001875, "cache_creation_input_token_cost_above_1hr": 0.00003, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "Claude", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "openrouter/openrouter/anthropic/claude-sonnet-4", "slug": "openrouter-openrouter-anthropic-claude-sonnet-4", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-sonnet-4", "displayName": "claude-sonnet-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 4800, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost": 3e-7, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "image", "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-sonnet-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost": 3e-7, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "Claude", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "openrouter/openrouter/anthropic/claude-sonnet-4.6", "slug": "openrouter-openrouter-anthropic-claude-sonnet-4-6", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-sonnet-4.6", "displayName": "claude-sonnet-4.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost": 3e-7, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token": 0.000015, "output_cost_per_token_above_200k_tokens": 0.0000225 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-sonnet-4.6", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/anthropic/claude-sonnet-4.6" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost": 3e-7, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_above_200k_tokens": 0.0000225, "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "supports_minimal_reasoning_effort": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "Claude", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "openrouter/openrouter/anthropic/claude-opus-4.5", "slug": "openrouter-openrouter-anthropic-claude-opus-4-5", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-opus-4.5", "displayName": "claude-opus-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "minimal_reasoning_effort": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-opus-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000025, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "tokenizer": "Claude", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "openrouter/openrouter/anthropic/claude-opus-4.6", "slug": "openrouter-openrouter-anthropic-claude-opus-4-6", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-opus-4.6", "displayName": "claude-opus-4.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-opus-4.6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_minimal_reasoning_effort": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "Claude", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "openrouter/openrouter/anthropic/claude-sonnet-4.5", "slug": "openrouter-openrouter-anthropic-claude-sonnet-4-5", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-sonnet-4.5", "displayName": "claude-sonnet-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 4800, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 1000000, "maxInputTokens": 1000000, "maxOutputTokens": 1000000, "maxTokens": 1000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-sonnet-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "Claude", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "openrouter/openrouter/anthropic/claude-haiku-4.5", "slug": "openrouter-openrouter-anthropic-claude-haiku-4-5", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-haiku-4.5", "displayName": "claude-haiku-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": 1.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000125, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 200000, "maxInputTokens": 200000, "maxOutputTokens": 200000, "maxTokens": 200000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-haiku-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000125, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 0.000005, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "Claude", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "openrouter/openrouter/anthropic/claude-opus-4.7", "slug": "openrouter-openrouter-anthropic-claude-opus-4-7", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "claude-opus-4.7", "displayName": "claude-opus-4.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": true, "xhigh": true }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/anthropic/claude-opus-4.7", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "Claude", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "openrouter/openrouter/bytedance/ui-tars-1.5-7b", "slug": "openrouter-openrouter-bytedance-ui-tars-1-5-7b", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "ui-tars-1.5-7b", "displayName": "ui-tars-1.5-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 131072, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/bytedance/ui-tars-1.5-7b", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", "supports_tool_choice": true, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/deepseek/deepseek-chat", "slug": "openrouter-openrouter-deepseek-deepseek-chat", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "deepseek-chat", "displayName": "deepseek-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.14, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.14, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65536, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "prompt_caching": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/deepseek/deepseek-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.4e-7, "litellm_provider": "openrouter", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.8e-7, "supports_prompt_caching": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "DeepSeek", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/deepseek/deepseek-chat-v3-0324", "slug": "openrouter-openrouter-deepseek-deepseek-chat-v3-0324", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "deepseek-chat-v3-0324", "displayName": "deepseek-chat-v3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.14, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.14, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65536, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "prompt_caching": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/deepseek/deepseek-chat-v3-0324", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.4e-7, "litellm_provider": "openrouter", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.8e-7, "supports_prompt_caching": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "DeepSeek", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/deepseek/deepseek-chat-v3.1", "slug": "openrouter-openrouter-deepseek-deepseek-chat-v3-1", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "deepseek-chat-v3.1", "displayName": "deepseek-chat-v3.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "input_cost_per_token_cache_hit": 2e-8, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/deepseek/deepseek-chat-v3.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "input_cost_per_token_cache_hit": 2e-8, "litellm_provider": "openrouter", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 8e-7, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "DeepSeek", "instruct_type": "deepseek-v3.1" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/deepseek/deepseek-v3.2", "slug": "openrouter-openrouter-deepseek-deepseek-v3-2", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "deepseek-v3.2", "displayName": "deepseek-v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.28, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.028, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.28, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.8e-7, "input_cost_per_token_cache_hit": 2.8e-8, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/deepseek/deepseek-v3.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.8e-7, "input_cost_per_token_cache_hit": 2.8e-8, "litellm_provider": "openrouter", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 4e-7, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "DeepSeek", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "openrouter/openrouter/deepseek/deepseek-v3.2-exp", "slug": "openrouter-openrouter-deepseek-deepseek-v3-2-exp", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "deepseek-v3.2-exp", "displayName": "deepseek-v3.2-exp", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "input_cost_per_token_cache_hit": 2e-8, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": false, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/deepseek/deepseek-v3.2-exp", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "input_cost_per_token_cache_hit": 2e-8, "litellm_provider": "openrouter", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 4e-7, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "DeepSeek", "instruct_type": "deepseek-v3.1" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "openrouter/openrouter/deepseek/deepseek-r1", "slug": "openrouter-openrouter-deepseek-deepseek-r1", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "deepseek-r1", "displayName": "deepseek-r1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.55, "outputUsdPer1MTokens": 2.1900000000000004, "cachedInputUsdPer1MTokens": 0.14, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.55, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-7, "input_cost_per_token_cache_hit": 1.4e-7, "output_cost_per_token": 0.00000219 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65336, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/deepseek/deepseek-r1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5.5e-7, "input_cost_per_token_cache_hit": 1.4e-7, "litellm_provider": "openrouter", "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000219, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "DeepSeek", "instruct_type": "deepseek-r1" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "openrouter/openrouter/deepseek/deepseek-r1-0528", "slug": "openrouter-openrouter-deepseek-deepseek-r1-0528", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "deepseek-r1-0528", "displayName": "deepseek-r1-0528", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 2.1500000000000004, "cachedInputUsdPer1MTokens": 0.14, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "input_cost_per_token_cache_hit": 1.4e-7, "output_cost_per_token": 0.00000215 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65336, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/deepseek/deepseek-r1-0528", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "input_cost_per_token_cache_hit": 1.4e-7, "litellm_provider": "openrouter", "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000215, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "DeepSeek", "instruct_type": "deepseek-r1" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "openrouter/openrouter/google/gemini-2.0-flash-001", "slug": "openrouter-openrouter-google-gemini-2-0-flash-001", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gemini-2.0-flash-001", "displayName": "gemini-2.0-flash-001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.7, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": true, "function_calling": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "audio", "file", "image", "text", "video" ], "input": [ "text", "image", "file", "audio", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01" }, "source": { "type": "litellm", "litellmKey": "openrouter/google/gemini-2.0-flash-001", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 4e-7, "supports_audio_output": true, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file+audio+video->text", "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "tokenizer": "Gemini", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." } } }, { "id": "openrouter/openrouter/google/gemini-2.5-flash", "slug": "openrouter-openrouter-google-gemini-2-5-flash", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gemini-2.5-flash", "displayName": "gemini-2.5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.7, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": true, "function_calling": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "audio", "file", "image", "text", "video" ], "input": [ "file", "image", "text", "audio", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/google/gemini-2.5-flash", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 3e-7, "litellm_provider": "openrouter", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.0000025, "supports_audio_output": true, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file+audio+video->text", "input_modalities": [ "file", "image", "text", "audio", "video" ], "output_modalities": [ "text" ], "tokenizer": "Gemini", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/google/gemini-2.5-pro", "slug": "openrouter-openrouter-google-gemini-2-5-pro", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gemini-2.5-pro", "displayName": "gemini-2.5-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.7, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": true, "function_calling": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "audio", "file", "image", "text", "video" ], "input": [ "text", "image", "file", "audio", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/google/gemini-2.5-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openrouter", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, "supports_audio_output": true, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file+audio+video->text", "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "tokenizer": "Gemini", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "openrouter/openrouter/google/gemini-3-pro-preview", "slug": "openrouter-openrouter-google-gemini-3-pro-preview", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gemini-3-pro-preview", "displayName": "gemini-3-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/google/gemini-3-pro-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "litellm_provider": "openrouter", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "openrouter/openrouter/google/gemini-3-flash-preview", "slug": "openrouter-openrouter-google-gemini-3-flash-preview", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gemini-3-flash-preview", "displayName": "gemini-3-flash-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 3, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 5e-7, "output_cost_per_reasoning_token": 0.000003, "output_cost_per_token": 0.000003, "rpm": 2000, "tpm": 800000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "file", "image", "text", "video" ], "input": [ "text", "image", "file", "audio", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/google/gemini-3-flash-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing/gemini-3" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 5e-7, "litellm_provider": "openrouter", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.000003, "output_cost_per_token": 0.000003, "rpm": 2000, "source": "https://ai.google.dev/pricing/gemini-3", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000, "openrouter_architecture": { "modality": "text+image+file+audio+video->text", "input_modalities": [ "text", "image", "file", "audio", "video" ], "output_modalities": [ "text" ], "tokenizer": "Gemini", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_resolved_gemini3flashhighreasoning_benchmarkleaderboard_215": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash (high reasoning)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_gemini3flashpreviewhigh_benchmarkleaderboard_234": { "label": "LiveBench", "category": "general_knowledge", "score": 72.4, "scoreText": "72.40", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash Preview High", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific high-effort variant." } } }, { "id": "openrouter/openrouter/google/gemini-3.1-flash-lite-preview", "slug": "openrouter-openrouter-google-gemini-3-1-flash-lite-preview", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gemini-3.1-flash-lite-preview", "displayName": "gemini-3.1-flash-lite-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 1.5, "audioInputUsdPer1MTokens": 0.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "rpm": 2000, "tpm": 800000 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": false, "code_execution": true, "file_search": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "file", "image", "text", "video" ], "input": [ "text", "image", "video", "file", "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/google/gemini-3.1-flash-lite-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing/gemini-3" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "litellm_provider": "openrouter", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "rpm": 2000, "source": "https://ai.google.dev/pricing/gemini-3", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_code_execution": true, "supports_file_search": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000, "openrouter_architecture": { "modality": "text+image+file+audio+video->text", "input_modalities": [ "text", "image", "video", "file", "audio" ], "output_modalities": [ "text" ], "tokenizer": "Gemini", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/google/gemini-3.1-flash-lite", "slug": "openrouter-openrouter-google-gemini-3-1-flash-lite", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gemini-3.1-flash-lite", "displayName": "gemini-3.1-flash-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 1.5, "audioInputUsdPer1MTokens": 0.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "rpm": 2000, "tpm": 800000 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": false, "code_execution": true, "file_search": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "file", "image", "text", "video" ], "input": [ "text", "image", "video", "file", "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/google/gemini-3.1-flash-lite", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "litellm_provider": "openrouter", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_code_execution": true, "supports_file_search": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000, "openrouter_architecture": { "modality": "text+image+file+audio+video->text", "input_modalities": [ "text", "image", "video", "file", "audio" ], "output_modalities": [ "text" ], "tokenizer": "Gemini", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/google/gemini-3.1-pro-preview", "slug": "openrouter-openrouter-google-gemini-3-1-pro-preview", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gemini-3.1-pro-preview", "displayName": "gemini-3.1-pro-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 4, "above200kOutputUsdPer1MTokens": 18, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "audio", "file", "image", "text", "video" ], "input": [ "audio", "file", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/google/gemini-3.1-pro-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/google/gemini-3.1-pro-preview" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_200k_tokens": 0.000018, "source": "https://openrouter.ai/google/gemini-3.1-pro-preview", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file+audio+video->text", "input_modalities": [ "audio", "file", "image", "text", "video" ], "output_modalities": [ "text" ], "tokenizer": "Gemini", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "livebench_livebenchscore_gemini31propreviewhigh_benchmarkleaderboard_229": { "label": "LiveBench", "category": "general_knowledge", "score": 79.93, "scoreText": "79.93", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview High*", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; source notes this row as a high-effort variant." }, "lmarenatextarenaenglish_arenaelo_gemini31propreview_benchmarkleaderboard_240": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1490, "scoreText": "1490±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "gemini-3.1-pro-preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "gpqadiamond_accuracy_gemini31propreview_benchmarkleaderboard_245": { "label": "GPQA Diamond", "category": "science", "score": 94.1, "scoreText": "94.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/gpqa-diamond", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Top row summarized on the Artificial Analysis GPQA Diamond leaderboard." }, "mmmupro_accuracy_gemini31propreview_benchmarkleaderboard_253": { "label": "MMMU-Pro", "category": "multimodal", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmmu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3.1 Pro Preview", "exactModelOrSnapshot": "Gemini 3.1 Pro Preview", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Artificial Analysis MMMU-Pro leaderboard row shown without a route qualifier." } } }, { "id": "openrouter/openrouter/gryphe/mythomax-l2-13b", "slug": "openrouter-openrouter-gryphe-mythomax-l2-13b", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "mythomax-l2-13b", "displayName": "mythomax-l2-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.875, "outputUsdPer1MTokens": 1.875, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.875, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001875, "output_cost_per_token": 0.000001875 } }, "limits": { "contextWindow": 8192, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/gryphe/mythomax-l2-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001875, "litellm_provider": "openrouter", "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000001875, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Llama2", "instruct_type": "alpaca" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/mancer/weaver", "slug": "openrouter-openrouter-mancer-weaver", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "weaver", "displayName": "weaver", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.625, "outputUsdPer1MTokens": 5.625, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.625, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005625, "output_cost_per_token": 0.000005625 } }, "limits": { "contextWindow": 2000, "maxInputTokens": 8000, "maxOutputTokens": 2000, "maxTokens": 2000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mancer/weaver", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000005625, "litellm_provider": "openrouter", "max_tokens": 2000, "mode": "chat", "output_cost_per_token": 0.000005625, "supports_tool_choice": true, "max_input_tokens": 8000, "max_output_tokens": 2000, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Llama2", "instruct_type": "alpaca" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/meta-llama/llama-3-70b-instruct", "slug": "openrouter-openrouter-meta-llama-llama-3-70b-instruct", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "llama-3-70b-instruct", "displayName": "llama-3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.59, "outputUsdPer1MTokens": 0.7899999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.59, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.9e-7, "output_cost_per_token": 7.9e-7 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 8192, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/meta-llama/llama-3-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5.9e-7, "litellm_provider": "openrouter", "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 7.9e-7, "supports_tool_choice": true, "max_input_tokens": 8192, "max_output_tokens": 8000, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Llama3", "instruct_type": "llama3" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/minimax/minimax-m2", "slug": "openrouter-openrouter-minimax-minimax-m2", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "minimax-m2", "displayName": "minimax-m2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.255, "outputUsdPer1MTokens": 1.02, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.255, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.55e-7, "output_cost_per_token": 0.00000102 } }, "limits": { "contextWindow": 204800, "maxInputTokens": 204800, "maxOutputTokens": 204800, "maxTokens": 204800, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/minimax/minimax-m2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.55e-7, "litellm_provider": "openrouter", "max_input_tokens": 204800, "max_output_tokens": 204800, "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 0.00000102, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "openrouter/openrouter/mistralai/devstral-2512", "slug": "openrouter-openrouter-mistralai-devstral-2512", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "devstral-2512", "displayName": "devstral-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262144, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": false, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "file", "text" ], "input": [ "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mistralai/devstral-2512", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "input_cost_per_token": 1.5e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_prompt_caching": false, "supports_tool_choice": true, "supports_vision": false, "openrouter_architecture": { "modality": "text+file->text", "input_modalities": [ "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "Mistral", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "openrouter/openrouter/mistralai/ministral-3b-2512", "slug": "openrouter-openrouter-mistralai-ministral-3b-2512", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "ministral-3b-2512", "displayName": "ministral-3b-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mistralai/ministral-3b-2512", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_prompt_caching": false, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "Mistral", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/mistralai/ministral-8b-2512", "slug": "openrouter-openrouter-mistralai-ministral-8b-2512", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "ministral-8b-2512", "displayName": "ministral-8b-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mistralai/ministral-8b-2512", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "input_cost_per_token": 1.5e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-7, "supports_function_calling": true, "supports_prompt_caching": false, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "Mistral", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/mistralai/ministral-14b-2512", "slug": "openrouter-openrouter-mistralai-ministral-14b-2512", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "ministral-14b-2512", "displayName": "ministral-14b-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mistralai/ministral-14b-2512", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "input_cost_per_token": 2e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-7, "supports_function_calling": true, "supports_prompt_caching": false, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "Mistral", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/mistralai/mistral-large-2512", "slug": "openrouter-openrouter-mistralai-mistral-large-2512", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "mistral-large-2512", "displayName": "mistral-large-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": false, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mistralai/mistral-large-2512", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "input_cost_per_token": 5e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_prompt_caching": false, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "Mistral", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/mistralai/mistral-7b-instruct", "slug": "openrouter-openrouter-mistralai-mistral-7b-instruct", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "mistral-7b-instruct", "displayName": "mistral-7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.13, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 1.3e-7 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32768, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mistralai/mistral-7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.3e-7, "litellm_provider": "openrouter", "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.3e-7, "supports_tool_choice": true, "max_input_tokens": 32768, "max_output_tokens": 8191 }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "openrouter/openrouter/mistralai/mistral-large", "slug": "openrouter-openrouter-mistralai-mistral-large", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "mistral-large", "displayName": "mistral-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8, "outputUsdPer1MTokens": 24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 128000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "file", "text" ], "input": [ "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mistralai/mistral-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000008, "litellm_provider": "openrouter", "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000024, "supports_tool_choice": true, "max_input_tokens": 128000, "max_output_tokens": 8191, "openrouter_architecture": { "modality": "text+file->text", "input_modalities": [ "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "Mistral", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/mistralai/mistral-small-3.1-24b-instruct", "slug": "openrouter-openrouter-mistralai-mistral-small-3-1-24b-instruct", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "mistral-small-3.1-24b-instruct", "displayName": "mistral-small-3.1-24b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mistralai/mistral-small-3.1-24b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-7, "supports_tool_choice": true, "max_input_tokens": 131072, "max_output_tokens": 131072, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "Mistral", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "mmlu_accuracy_mistralsmall3_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 81, "scoreText": "81%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mistral-small-3", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3", "exactModelOrSnapshot": "mistral-small-3", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is stated in the announcement text." }, "local_mmlu_accuracy_mistralsmall3124binstruct2503_officialmodelcard_281": { "label": "MMLU", "category": "general_knowledge", "score": 80.62, "scoreText": "80.62%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3.1", "exactModelOrSnapshot": "Mistral-Small-3.1-24B-Instruct-2503", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "medium", "note": "Instruction eval table in the model card; percentages are printed as-is." }, "local_math_accuracy_mistralsmall3124binstruct2503_officialmodelcard_282": { "label": "MATH", "category": "math", "score": 69.3, "scoreText": "69.30%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3.1", "exactModelOrSnapshot": "Mistral-Small-3.1-24B-Instruct-2503", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "medium", "note": "Instruction eval table in the model card; percentages are printed as-is." }, "local_humaneval_pass1_mistralsmall3124binstruct2503_officialmodelcard_283": { "label": "HumanEval", "category": "coding", "score": 88.41, "scoreText": "88.41%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3.1", "exactModelOrSnapshot": "Mistral-Small-3.1-24B-Instruct-2503", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "medium", "note": "Instruction eval table in the model card; percentages are printed as-is." }, "local_longbenchv2_score_mistralsmall3124binstruct2503_officialmodelcard_284": { "label": "LongBench v2", "category": "long_context", "score": 37.18, "scoreText": "37.18%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3.1", "exactModelOrSnapshot": "Mistral-Small-3.1-24B-Instruct-2503", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "medium", "note": "Long-context eval table in the model card; percentages are printed as-is." } } }, { "id": "openrouter/openrouter/mistralai/mistral-small-3.2-24b-instruct", "slug": "openrouter-openrouter-mistralai-mistral-small-3-2-24b-instruct", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "mistral-small-3.2-24b-instruct", "displayName": "mistral-small-3.2-24b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mistralai/mistral-small-3.2-24b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-7, "supports_tool_choice": true, "max_input_tokens": 128000, "max_output_tokens": 128000, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "image", "text" ], "output_modalities": [ "text" ], "tokenizer": "Mistral", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "mmlu_accuracy_mistralsmall3_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 81, "scoreText": "81%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mistral-small-3", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3", "exactModelOrSnapshot": "mistral-small-3", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is stated in the announcement text." } } }, { "id": "openrouter/openrouter/mistralai/mixtral-8x22b-instruct", "slug": "openrouter-openrouter-mistralai-mixtral-8x22b-instruct", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "mixtral-8x22b-instruct", "displayName": "mixtral-8x22b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.65, "outputUsdPer1MTokens": 0.65, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 6.5e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "file", "text" ], "input": [ "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/mistralai/mixtral-8x22b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6.5e-7, "litellm_provider": "openrouter", "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6.5e-7, "supports_tool_choice": true, "max_input_tokens": 65536, "max_output_tokens": 65536, "openrouter_architecture": { "modality": "text+file->text", "input_modalities": [ "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "Mistral", "instruct_type": "mistral" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "gsm8kmaj8_8shot_mixtral8x22binstruct_officiallaunchpost_212": { "label": "GSM8K maj@8", "category": "math", "score": 90.8, "scoreText": "90.8%", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on GSM8K maj@8." }, "mathmaj4_4shot_mixtral8x22binstruct_officiallaunchpost_213": { "label": "Math maj@4", "category": "math", "score": 44.6, "scoreText": "44.6%", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on Math maj@4." } } }, { "id": "openrouter/openrouter/moonshotai/kimi-k2.5", "slug": "openrouter-openrouter-moonshotai-kimi-k2-5", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "kimi-k2.5", "displayName": "kimi-k2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "video_input": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/moonshotai/kimi-k2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/moonshotai/kimi-k2.5" }, "rawLitellm": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 6e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://openrouter.ai/moonshotai/kimi-k2.5", "supports_function_calling": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "openrouter/openrouter/openai/gpt-3.5-turbo", "slug": "openrouter-openrouter-openai-gpt-3-5-turbo", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-3.5-turbo", "displayName": "gpt-3.5-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-3.5-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000015, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000002, "supports_tool_choice": true, "max_input_tokens": 16385, "max_output_tokens": 4096, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/openai/gpt-3.5-turbo-16k", "slug": "openrouter-openrouter-openai-gpt-3-5-turbo-16k", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-3.5-turbo-16k", "displayName": "gpt-3.5-turbo-16k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-3.5-turbo-16k", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000004, "supports_tool_choice": true, "max_input_tokens": 16385, "max_output_tokens": 4096, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/openai/gpt-4", "slug": "openrouter-openrouter-openai-gpt-4", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-4", "displayName": "gpt-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 30, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 30, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8191, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00003, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00006, "supports_tool_choice": true, "max_input_tokens": 8191, "max_output_tokens": 4096, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/openai/gpt-4.1", "slug": "openrouter-openrouter-openai-gpt-4-1", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-4.1", "displayName": "gpt-4.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "image", "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-4.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "litellm_provider": "openrouter", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000008, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "openrouter/openrouter/openai/gpt-4.1-mini", "slug": "openrouter-openrouter-openai-gpt-4-1-mini", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-4.1-mini", "displayName": "gpt-4.1-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "image", "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-4.1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 4e-7, "litellm_provider": "openrouter", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000016, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gpt41mini_officiallaunchpost_5": { "label": "SWE-bench Verified", "category": "coding", "score": 23.6, "scoreText": "23.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-mini", "exactModelOrSnapshot": "GPT-4.1 mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table for the GPT-4.1 family." } } }, { "id": "openrouter/openrouter/openai/gpt-4.1-nano", "slug": "openrouter-openrouter-openai-gpt-4-1-nano", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-4.1-nano", "displayName": "gpt-4.1-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "image", "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-4.1-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "aime24_accuracy_gpt41nano_officiallaunchpost_6": { "label": "AIME 2024", "category": "reasoning", "score": 29.4, "scoreText": "29.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-nano", "exactModelOrSnapshot": "GPT-4.1 nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Academic-knowledge appendix comparison row for the nano model." }, "mmlu_accuracy_gpt41nano_officiallaunchpost_258": { "label": "MMLU", "category": "general_knowledge", "score": 80.1, "scoreText": "80.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the narrative and table." }, "gpqa_accuracy_gpt41nano_officiallaunchpost_259": { "label": "GPQA", "category": "reasoning", "score": 50.3, "scoreText": "50.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." }, "aiderpolyglotcoding_passrate_gpt41nano_officiallaunchpost_260": { "label": "Aider Polyglot", "category": "coding", "score": 9.8, "scoreText": "9.8%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." } } }, { "id": "openrouter/openrouter/openai/gpt-4o", "slug": "openrouter-openrouter-openai-gpt-4o", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-4o", "displayName": "gpt-4o", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-4o", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "openrouter", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openrouter/openrouter/openai/gpt-4o-2024-05-13", "slug": "openrouter-openrouter-openai-gpt-4o-2024-05-13", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-4o-2024-05-13", "displayName": "gpt-4o-2024-05-13", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-4o-2024-05-13", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "openrouter", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "openrouter/openrouter/openai/gpt-5-chat", "slug": "openrouter-openrouter-openai-gpt-5-chat", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-5-chat", "displayName": "gpt-5-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-5-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openrouter", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openrouter/openrouter/openai/gpt-5-codex", "slug": "openrouter-openrouter-openai-gpt-5-codex", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-5-codex", "displayName": "gpt-5-codex", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-5-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openrouter", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openrouter/openrouter/openai/gpt-5.2-codex", "slug": "openrouter-openrouter-openai-gpt-5-2-codex", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-5.2-codex", "displayName": "gpt-5.2-codex", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-5.2-codex", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "litellm_provider": "openrouter", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000014, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "openrouter/openrouter/openai/gpt-5", "slug": "openrouter-openrouter-openai-gpt-5", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-5", "displayName": "gpt-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openrouter", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openrouter/openrouter/openai/gpt-5-mini", "slug": "openrouter-openrouter-openai-gpt-5-mini", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-5-mini", "displayName": "gpt-5-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-5-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "litellm_provider": "openrouter", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000002, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "openrouter/openrouter/openai/gpt-5-nano", "slug": "openrouter-openrouter-openai-gpt-5-nano", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-5-nano", "displayName": "gpt-5-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.005, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-9, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-5-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 5e-9, "input_cost_per_token": 5e-8, "litellm_provider": "openrouter", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-7, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "aime2025_accuracy_gpt5nanohigh_officiallaunchpost_28": { "label": "AIME 2025", "category": "reasoning", "score": 85.2, "scoreText": "85.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-nano", "exactModelOrSnapshot": "GPT-5 nano (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." } } }, { "id": "openrouter/openrouter/openai/gpt-5.1-codex-max", "slug": "openrouter-openrouter-openai-gpt-5-1-codex-max", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-5.1-codex-max", "displayName": "gpt-5.1-codex-max", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 400000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-5.1-codex-max", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/openai/gpt-5.1-codex-max" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openrouter", "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "source": "https://openrouter.ai/openai/gpt-5.1-codex-max", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "openrouter/openrouter/openai/gpt-5.2", "slug": "openrouter-openrouter-openai-gpt-5-2", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-5.2", "displayName": "gpt-5.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-5.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "litellm_provider": "openrouter", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000014, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "openrouter/openrouter/openai/gpt-5.2-chat", "slug": "openrouter-openrouter-openai-gpt-5-2-chat", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-5.2-chat", "displayName": "gpt-5.2-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.75, "outputUsdPer1MTokens": 14, "cachedInputUsdPer1MTokens": 0.175, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-5.2-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 0.00000175, "litellm_provider": "openrouter", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000014, "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "file", "image", "text" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "openrouter/openrouter/openai/gpt-5.2-pro", "slug": "openrouter-openrouter-openai-gpt-5-2-pro", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-5.2-pro", "displayName": "gpt-5.2-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 21, "outputUsdPer1MTokens": 168, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": false, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "image", "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-5.2-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0, "input_cost_per_token": 0.000021, "litellm_provider": "openrouter", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000168, "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "image", "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/openai/gpt-oss-120b", "slug": "openrouter-openrouter-openai-gpt-oss-120b", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-oss-120b", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/openai/gpt-oss-120b" }, "rawLitellm": { "input_cost_per_token": 1.8e-7, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-7, "source": "https://openrouter.ai/openai/gpt-oss-120b", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "openrouter/openrouter/openai/gpt-oss-20b", "slug": "openrouter-openrouter-openai-gpt-oss-20b", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "gpt-oss-20b", "displayName": "gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/gpt-oss-20b", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/openai/gpt-oss-20b" }, "rawLitellm": { "input_cost_per_token": 2e-8, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-7, "source": "https://openrouter.ai/openai/gpt-oss-20b", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "openrouter/openrouter/openai/o1", "slug": "openrouter-openrouter-openai-o1", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "openai", "displayName": "openai", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": 7.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "text", "image", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/o1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00006, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+file->text", "input_modalities": [ "text", "image", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/openai/o3-mini", "slug": "openrouter-openrouter-openai-o3-mini", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "o3-mini", "displayName": "o3-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 128000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "file", "text" ], "input": [ "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/o3-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000011, "litellm_provider": "openrouter", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false, "openrouter_architecture": { "modality": "text+file->text", "input_modalities": [ "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "aime2024_accuracy_o3minihigh_officiallaunchpost_18": { "label": "AIME 2024", "category": "reasoning", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "gpqadiamond_accuracy_o3minihigh_officiallaunchpost_19": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 77, "scoreText": "77.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "swebenchverified_accuracy_o3minihigh_officiallaunchpost_20": { "label": "SWE-bench Verified", "category": "coding", "score": 48.9, "scoreText": "48.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; n=477 verified tasks." } } }, { "id": "openrouter/openrouter/openai/o3-mini-high", "slug": "openrouter-openrouter-openai-o3-mini-high", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "o3-mini-high", "displayName": "o3-mini-high", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 128000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [ "file", "text" ], "input": [ "text", "file" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openai/o3-mini-high", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000011, "litellm_provider": "openrouter", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false, "openrouter_architecture": { "modality": "text+file->text", "input_modalities": [ "text", "file" ], "output_modalities": [ "text" ], "tokenizer": "GPT", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "aime2024_accuracy_o3minihigh_officiallaunchpost_18": { "label": "AIME 2024", "category": "reasoning", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "gpqadiamond_accuracy_o3minihigh_officiallaunchpost_19": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 77, "scoreText": "77.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "swebenchverified_accuracy_o3minihigh_officiallaunchpost_20": { "label": "SWE-bench Verified", "category": "coding", "score": 48.9, "scoreText": "48.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; n=477 verified tasks." } } }, { "id": "openrouter/openrouter/qwen/qwen-2.5-coder-32b-instruct", "slug": "openrouter-openrouter-qwen-qwen-2-5-coder-32b-instruct", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen-2.5-coder-32b-instruct", "displayName": "qwen-2.5-coder-32b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": 0.18, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 1.8e-7 } }, "limits": { "contextWindow": 33792, "maxInputTokens": 33792, "maxOutputTokens": 33792, "maxTokens": 33792, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen-2.5-coder-32b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.8e-7, "litellm_provider": "openrouter", "max_input_tokens": 33792, "max_output_tokens": 33792, "max_tokens": 33792, "mode": "chat", "output_cost_per_token": 1.8e-7, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Qwen", "instruct_type": "chatml" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_aiderpolyglot_percentcorrect_qwen25coder32binstruct_benchmarkleaderboard_247": { "label": "Aider Polyglot", "category": "agentic", "score": 16.4, "scoreText": "16.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-Coder", "exactModelOrSnapshot": "Qwen2.5-Coder-32B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the 32B instruct checkpoint." } } }, { "id": "openrouter/openrouter/qwen/qwen-vl-plus", "slug": "openrouter-openrouter-qwen-qwen-vl-plus", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen-vl-plus", "displayName": "qwen-vl-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.21, "outputUsdPer1MTokens": 0.63, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.21, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.1e-7, "output_cost_per_token": 6.3e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 8192, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen-vl-plus", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.1e-7, "litellm_provider": "openrouter", "max_input_tokens": 8192, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 6.3e-7, "supports_tool_choice": true, "supports_vision": true } }, { "id": "openrouter/openrouter/qwen/qwen3-coder", "slug": "openrouter-openrouter-qwen-qwen3-coder", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3-coder", "displayName": "qwen3-coder", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.95, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 9.5e-7 } }, "limits": { "contextWindow": 262100, "maxInputTokens": 262100, "maxOutputTokens": 262100, "maxTokens": 262100, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3-coder", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3-coder" }, "rawLitellm": { "input_cost_per_token": 2.2e-7, "litellm_provider": "openrouter", "max_input_tokens": 262100, "max_output_tokens": 262100, "max_tokens": 262100, "mode": "chat", "output_cost_per_token": 9.5e-7, "source": "https://openrouter.ai/qwen/qwen3-coder", "supports_tool_choice": true, "supports_function_calling": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "openrouter/openrouter/qwen/qwen3-coder-plus", "slug": "openrouter-openrouter-qwen-qwen3-coder-plus", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3-coder-plus", "displayName": "qwen3-coder-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 997952, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3-coder-plus", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3-coder-plus" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "openrouter", "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://openrouter.ai/qwen/qwen3-coder-plus", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "openrouter/openrouter/qwen/qwen3-235b-a22b-2507", "slug": "openrouter-openrouter-qwen-qwen3-235b-a22b-2507", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3-235b-a22b-2507", "displayName": "qwen3-235b-a22b-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.071, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.071, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.1e-8, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3-235b-a22b-2507", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507" }, "rawLitellm": { "input_cost_per_token": 7.1e-8, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1e-7, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", "supports_function_calling": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/qwen/qwen3-235b-a22b-thinking-2507", "slug": "openrouter-openrouter-qwen-qwen3-235b-a22b-thinking-2507", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3-235b-a22b-thinking-2507", "displayName": "qwen3-235b-a22b-thinking-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.11, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.11, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.1e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3-235b-a22b-thinking-2507", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507" }, "rawLitellm": { "input_cost_per_token": 1.1e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": "qwen3" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/qwen/qwen3.6-plus", "slug": "openrouter-openrouter-qwen-qwen3-6-plus", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3.6-plus", "displayName": "qwen3.6-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.325, "outputUsdPer1MTokens": 1.95, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.325, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.25e-7, "output_cost_per_token": 0.00000195 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1000000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "text", "image", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3.6-plus", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3.6-plus" }, "rawLitellm": { "input_cost_per_token": 3.25e-7, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.00000195, "source": "https://openrouter.ai/qwen/qwen3.6-plus", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+video->text", "input_modalities": [ "text", "image", "video" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/qwen/qwen3.5-35b-a3b", "slug": "openrouter-openrouter-qwen-qwen3-5-35b-a3b", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3.5-35b-a3b", "displayName": "qwen3.5-35b-a3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262144, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "text", "image", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3.5-35b-a3b", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3.5-35b-a3b" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+video->text", "input_modalities": [ "text", "image", "video" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/qwen/qwen3.5-27b", "slug": "openrouter-openrouter-qwen-qwen3-5-27b", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3.5-27b", "displayName": "qwen3.5-27b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262144, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "text", "image", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3.5-27b", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3.5-27b" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000024, "source": "https://openrouter.ai/qwen/qwen3.5-27b", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+video->text", "input_modalities": [ "text", "image", "video" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "mmlupro_score_qwen3527b_officialmodelcard_157": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 86.1, "scoreText": "86.1", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3.5-27B", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3.5-27B", "exactModelOrSnapshot": "Qwen3.5-27B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the Qwen3.5-27B column in the comparison table." }, "gpqadiamond_score_qwen3527b_officialmodelcard_158": { "label": "GPQA Diamond", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3.5-27B", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3.5-27B", "exactModelOrSnapshot": "Qwen3.5-27B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the Qwen3.5-27B column in the comparison table." }, "livecodebenchv6_pass1_qwen3527b_officialmodelcard_159": { "label": "LiveCodeBench v6", "category": "coding", "score": 80.7, "scoreText": "80.7", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3.5-27B", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3.5-27B", "exactModelOrSnapshot": "Qwen3.5-27B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the Qwen3.5-27B column in the comparison table." } } }, { "id": "openrouter/openrouter/qwen/qwen3.5-122b-a10b", "slug": "openrouter-openrouter-qwen-qwen3-5-122b-a10b", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3.5-122b-a10b", "displayName": "qwen3.5-122b-a10b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262144, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "text", "image", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3.5-122b-a10b", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3.5-122b-a10b" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://openrouter.ai/qwen/qwen3.5-122b-a10b", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+video->text", "input_modalities": [ "text", "image", "video" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/qwen/qwen3.5-flash-02-23", "slug": "openrouter-openrouter-qwen-qwen3-5-flash-02-23", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3.5-flash-02-23", "displayName": "qwen3.5-flash-02-23", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1000000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "text", "image", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3.5-flash-02-23", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3.5-flash-02-23" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4e-7, "source": "https://openrouter.ai/qwen/qwen3.5-flash-02-23", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+video->text", "input_modalities": [ "text", "image", "video" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/qwen/qwen3.5-plus-02-15", "slug": "openrouter-openrouter-qwen-qwen3-5-plus-02-15", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3.5-plus-02-15", "displayName": "qwen3.5-plus-02-15", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "input_cost_per_token_above_256k_tokens": 5e-7, "output_cost_per_token": 0.0000024, "output_cost_per_token_above_256k_tokens": 0.000003 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1000000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "text", "image", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3.5-plus-02-15", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3.5-plus-02-15" }, "rawLitellm": { "input_cost_per_token": 4e-7, "input_cost_per_token_above_256k_tokens": 5e-7, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000024, "output_cost_per_token_above_256k_tokens": 0.000003, "source": "https://openrouter.ai/qwen/qwen3.5-plus-02-15", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+video->text", "input_modalities": [ "text", "image", "video" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/qwen/qwen3.5-397b-a17b", "slug": "openrouter-openrouter-qwen-qwen3-5-397b-a17b", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "qwen3.5-397b-a17b", "displayName": "qwen3.5-397b-a17b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3.5999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262144, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "text", "image", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/qwen/qwen3.5-397b-a17b", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/qwen/qwen3.5-397b-a17b" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000036, "source": "https://openrouter.ai/qwen/qwen3.5-397b-a17b", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image+video->text", "input_modalities": [ "text", "image", "video" ], "output_modalities": [ "text" ], "tokenizer": "Qwen3", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/switchpoint/router", "slug": "openrouter-openrouter-switchpoint-router", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "router", "displayName": "router", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.85, "outputUsdPer1MTokens": 3.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.85, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8.5e-7, "output_cost_per_token": 0.0000034 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/switchpoint/router", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/switchpoint/router" }, "rawLitellm": { "input_cost_per_token": 8.5e-7, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000034, "source": "https://openrouter.ai/switchpoint/router", "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/undi95/remm-slerp-l2-13b", "slug": "openrouter-openrouter-undi95-remm-slerp-l2-13b", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "remm-slerp-l2-13b", "displayName": "remm-slerp-l2-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.875, "outputUsdPer1MTokens": 1.875, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.875, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001875, "output_cost_per_token": 0.000001875 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 6144, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/undi95/remm-slerp-l2-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001875, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000001875, "supports_tool_choice": true, "max_input_tokens": 6144, "max_output_tokens": 4096, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Llama2", "instruct_type": "alpaca" }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/x-ai/grok-4", "slug": "openrouter-openrouter-x-ai-grok-4", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "grok-4", "displayName": "grok-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/x-ai/grok-4", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/x-ai/grok-4" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "openrouter", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://openrouter.ai/x-ai/grok-4", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "openrouter/openrouter/z-ai/glm-4.6", "slug": "openrouter-openrouter-z-ai-glm-4-6", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "glm-4.6", "displayName": "glm-4.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.00000175 } }, "limits": { "contextWindow": 131000, "maxInputTokens": 202800, "maxOutputTokens": 131000, "maxTokens": 131000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/z-ai/glm-4.6", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/z-ai/glm-4.6" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "openrouter", "max_input_tokens": 202800, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 0.00000175, "source": "https://openrouter.ai/z-ai/glm-4.6", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_zaiglm46_benchmarkleaderboard_282": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_zaiglm46_benchmarkleaderboard_283": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_zaiglm46_benchmarkleaderboard_284": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_zaiglm46_benchmarkleaderboard_285": { "label": "GPQA Diamond", "category": "reasoning", "score": 78, "scoreText": "78.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_artificialanalysisintelligenceindex_score_zaiglm46_benchmarkleaderboard_310": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysiscodingindex_score_zaiglm46_benchmarkleaderboard_311": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysisagenticindex_score_zaiglm46_benchmarkleaderboard_312": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." } } }, { "id": "openrouter/openrouter/z-ai/glm-4.6:exacto", "slug": "openrouter-openrouter-z-ai-glm-4-6-exacto", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "glm-4.6:exacto", "displayName": "glm-4.6:exacto", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.44999999999999996, "outputUsdPer1MTokens": 1.9, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.44999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.0000019 } }, "limits": { "contextWindow": 131000, "maxInputTokens": 202800, "maxOutputTokens": 131000, "maxTokens": 131000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/z-ai/glm-4.6:exacto", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/z-ai/glm-4.6:exacto" }, "rawLitellm": { "input_cost_per_token": 4.5e-7, "litellm_provider": "openrouter", "max_input_tokens": 202800, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 0.0000019, "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_zaiglm46_benchmarkleaderboard_282": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_zaiglm46_benchmarkleaderboard_283": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_zaiglm46_benchmarkleaderboard_284": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_zaiglm46_benchmarkleaderboard_285": { "label": "GPQA Diamond", "category": "reasoning", "score": 78, "scoreText": "78.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_artificialanalysisintelligenceindex_score_zaiglm46_benchmarkleaderboard_310": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysiscodingindex_score_zaiglm46_benchmarkleaderboard_311": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysisagenticindex_score_zaiglm46_benchmarkleaderboard_312": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." } } }, { "id": "openrouter/openrouter/xiaomi/mimo-v2-flash", "slug": "openrouter-openrouter-xiaomi-mimo-v2-flash", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "mimo-v2-flash", "displayName": "mimo-v2-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": 0.01, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1e-8 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 262144, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true, "vision": false, "prompt_caching": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/xiaomi/mimo-v2-flash", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1e-8, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false, "supports_prompt_caching": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/xiaomi/mimo-v2.5-pro", "slug": "openrouter-openrouter-xiaomi-mimo-v2-5-pro", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "mimo-v2.5-pro", "displayName": "mimo-v2.5-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 1048576, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true, "vision": false, "response_schema": true, "prompt_caching": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/xiaomi/mimo-v2.5-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2e-7, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false, "supports_response_schema": true, "supports_prompt_caching": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/xiaomi/mimo-v2.5", "slug": "openrouter-openrouter-xiaomi-mimo-v2-5", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "mimo-v2.5", "displayName": "mimo-v2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": 0.08, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 8e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 1048576, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": true, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true, "vision": true, "audio_input": true, "video_input": true, "response_schema": true, "prompt_caching": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "text", "audio", "image", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/xiaomi/mimo-v2.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 8e-8, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": true, "supports_audio_input": true, "supports_video_input": true, "supports_response_schema": true, "supports_prompt_caching": true, "openrouter_architecture": { "modality": "text+image+audio+video->text", "input_modalities": [ "text", "audio", "image", "video" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/z-ai/glm-4.7", "slug": "openrouter-openrouter-z-ai-glm-4-7", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "glm-4.7", "displayName": "glm-4.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "zero_raw_unclassified", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000015, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 202752, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true, "vision": true, "prompt_caching": false, "assistant_prefill": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/z-ai/glm-4.7", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000015, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0, "litellm_provider": "openrouter", "max_input_tokens": 202752, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": true, "supports_prompt_caching": false, "supports_assistant_prefill": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "openrouter/openrouter/z-ai/glm-4.7-flash", "slug": "openrouter-openrouter-z-ai-glm-4-7-flash", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "glm-4.7-flash", "displayName": "glm-4.7-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "zero_raw_unclassified", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 4e-7, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true, "vision": true, "prompt_caching": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/z-ai/glm-4.7-flash", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-8, "output_cost_per_token": 4e-7, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": true, "supports_prompt_caching": false, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "openrouter/openrouter/z-ai/glm-5", "slug": "openrouter-openrouter-z-ai-glm-5", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "glm-5", "displayName": "glm-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 2.56, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.00000256 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 202752, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/z-ai/glm-5", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/z-ai/glm-5" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "openrouter", "max_input_tokens": 202752, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000256, "source": "https://openrouter.ai/z-ai/glm-5", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "hle_score_glm5_officialmodelcard_165": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 30.5, "scoreText": "30.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "gpqadiamond_score_glm5_officialmodelcard_166": { "label": "GPQA Diamond", "category": "reasoning", "score": 86, "scoreText": "86.0", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchverified_score_glm5_officialmodelcard_167": { "label": "SWE-bench Verified", "category": "coding", "score": 77.8, "scoreText": "77.8", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "openrouter/openrouter/minimax/minimax-m2.1", "slug": "openrouter-openrouter-minimax-minimax-m2-1", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "minimax-m2.1", "displayName": "minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "zero_raw_unclassified", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.0000012, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 204000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true, "vision": true, "prompt_caching": false, "computer_use": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/minimax/minimax-m2.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.0000012, "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0, "litellm_provider": "openrouter", "max_input_tokens": 204000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": true, "supports_prompt_caching": false, "supports_computer_use": false, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "openrouter/openrouter/minimax/minimax-m2.5", "slug": "openrouter-openrouter-minimax-minimax-m2-5", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "minimax-m2.5", "displayName": "minimax-m2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.1, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000011, "cache_read_input_token_cost": 1.5e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 196608, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true, "vision": false, "prompt_caching": true, "computer_use": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/minimax/minimax-m2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://openrouter.ai/minimax/minimax-m2.5" }, "rawLitellm": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000011, "cache_read_input_token_cost": 1.5e-7, "litellm_provider": "openrouter", "max_input_tokens": 196608, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "source": "https://openrouter.ai/minimax/minimax-m2.5", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false, "supports_prompt_caching": true, "supports_computer_use": false, "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "openrouter/openrouter/openrouter/auto", "slug": "openrouter-openrouter-openrouter-auto", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "auto", "displayName": "auto", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": null, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": true, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true, "response_schema": true, "vision": true, "audio_input": true, "video_input": true } }, "modalities": { "supported": [ "audio", "file", "image", "text", "video" ], "input": [ "text", "image", "audio", "file", "video" ], "output": [ "text", "image" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openrouter/auto", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "openrouter", "max_input_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_audio_input": true, "supports_video_input": true, "openrouter_architecture": { "modality": "text+image+file+audio+video->text+image", "input_modalities": [ "text", "image", "audio", "file", "video" ], "output_modalities": [ "text", "image" ], "tokenizer": "Router", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/openrouter/free", "slug": "openrouter-openrouter-openrouter-free", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "free", "displayName": "free", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 200000, "maxInputTokens": 200000, "maxOutputTokens": null, "maxTokens": 200000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openrouter/free", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "openrouter", "max_input_tokens": 200000, "max_tokens": 200000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "openrouter_architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "Router", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "openrouter/openrouter/openrouter/bodybuilder", "slug": "openrouter-openrouter-openrouter-bodybuilder", "provider": "OpenRouter", "providerSlug": "openrouter", "name": "bodybuilder", "displayName": "bodybuilder", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openrouter/openrouter/bodybuilder", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "openrouter", "max_input_tokens": 128000, "max_tokens": 128000, "mode": "chat", "openrouter_architecture": { "modality": "text->text", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Router", "instruct_type": null }, "openrouter_modalities_source_url": "https://openrouter.ai/api/v1/models", "openrouter_modalities_fetched_at": "2026-05-27T17:54:00.162Z" } }, { "id": "ovhcloud/ovhcloud/DeepSeek-R1-Distill-Llama-70B", "slug": "ovhcloud-ovhcloud-deepseek-r1-distill-llama-70b", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "DeepSeek-R1-Distill-Llama-70B", "displayName": "DeepSeek-R1-Distill-Llama-70B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.67, "outputUsdPer1MTokens": 0.67, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.67, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.7e-7, "output_cost_per_token": 6.7e-7 } }, "limits": { "contextWindow": 131000, "maxInputTokens": 131000, "maxOutputTokens": 131000, "maxTokens": 131000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/DeepSeek-R1-Distill-Llama-70B", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b" }, "rawLitellm": { "input_cost_per_token": 6.7e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "ovhcloud/ovhcloud/Llama-3.1-8B-Instruct", "slug": "ovhcloud-ovhcloud-llama-3-1-8b-instruct", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "Llama-3.1-8B-Instruct", "displayName": "Llama-3.1-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131000, "maxInputTokens": 131000, "maxOutputTokens": 131000, "maxTokens": 131000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/Llama-3.1-8B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "ovhcloud/ovhcloud/Meta-Llama-3_1-70B-Instruct", "slug": "ovhcloud-ovhcloud-meta-llama-3_1-70b-instruct", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "Meta-Llama-3_1-70B-Instruct", "displayName": "Meta-Llama-3_1-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.67, "outputUsdPer1MTokens": 0.67, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.67, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.7e-7, "output_cost_per_token": 6.7e-7 } }, "limits": { "contextWindow": 131000, "maxInputTokens": 131000, "maxOutputTokens": 131000, "maxTokens": 131000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": false, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/Meta-Llama-3_1-70B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct" }, "rawLitellm": { "input_cost_per_token": 6.7e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct", "supports_function_calling": false, "supports_response_schema": false, "supports_tool_choice": false }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "ovhcloud/ovhcloud/Meta-Llama-3_3-70B-Instruct", "slug": "ovhcloud-ovhcloud-meta-llama-3_3-70b-instruct", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "Meta-Llama-3_3-70B-Instruct", "displayName": "Meta-Llama-3_3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.67, "outputUsdPer1MTokens": 0.67, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.67, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.7e-7, "output_cost_per_token": 6.7e-7 } }, "limits": { "contextWindow": 131000, "maxInputTokens": 131000, "maxOutputTokens": 131000, "maxTokens": 131000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/Meta-Llama-3_3-70B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct" }, "rawLitellm": { "input_cost_per_token": 6.7e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "ovhcloud/ovhcloud/Mistral-7B-Instruct-v0.3", "slug": "ovhcloud-ovhcloud-mistral-7b-instruct-v0-3", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "Mistral-7B-Instruct-v0.3", "displayName": "Mistral-7B-Instruct-v0.3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 127000, "maxInputTokens": 127000, "maxOutputTokens": 127000, "maxTokens": 127000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/Mistral-7B-Instruct-v0.3", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 127000, "max_output_tokens": 127000, "max_tokens": 127000, "mode": "chat", "output_cost_per_token": 1e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "ovhcloud/ovhcloud/Mistral-Nemo-Instruct-2407", "slug": "ovhcloud-ovhcloud-mistral-nemo-instruct-2407", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "Mistral-Nemo-Instruct-2407", "displayName": "Mistral-Nemo-Instruct-2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.13, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 1.3e-7 } }, "limits": { "contextWindow": 118000, "maxInputTokens": 118000, "maxOutputTokens": 118000, "maxTokens": 118000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/Mistral-Nemo-Instruct-2407", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407" }, "rawLitellm": { "input_cost_per_token": 1.3e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 118000, "max_output_tokens": 118000, "max_tokens": 118000, "mode": "chat", "output_cost_per_token": 1.3e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "ovhcloud/ovhcloud/Mistral-Small-3.2-24B-Instruct-2506", "slug": "ovhcloud-ovhcloud-mistral-small-3-2-24b-instruct-2506", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "Mistral-Small-3.2-24B-Instruct-2506", "displayName": "Mistral-Small-3.2-24B-Instruct-2506", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506" }, "rawLitellm": { "input_cost_per_token": 9e-8, "litellm_provider": "ovhcloud", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmlu_accuracy_mistralsmall3_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 81, "scoreText": "81%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mistral-small-3", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3", "exactModelOrSnapshot": "mistral-small-3", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is stated in the announcement text." } } }, { "id": "ovhcloud/ovhcloud/Mixtral-8x7B-Instruct-v0.1", "slug": "ovhcloud-ovhcloud-mixtral-8x7b-instruct-v0-1", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "Mixtral-8x7B-Instruct-v0.1", "displayName": "Mixtral-8x7B-Instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.63, "outputUsdPer1MTokens": 0.63, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.63, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.3e-7, "output_cost_per_token": 6.3e-7 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/Mixtral-8x7B-Instruct-v0.1", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1" }, "rawLitellm": { "input_cost_per_token": 6.3e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.3e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false } }, { "id": "ovhcloud/ovhcloud/Qwen2.5-Coder-32B-Instruct", "slug": "ovhcloud-ovhcloud-qwen2-5-coder-32b-instruct", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "Qwen2.5-Coder-32B-Instruct", "displayName": "Qwen2.5-Coder-32B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.87, "outputUsdPer1MTokens": 0.87, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.87, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8.7e-7, "output_cost_per_token": 8.7e-7 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/Qwen2.5-Coder-32B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct" }, "rawLitellm": { "input_cost_per_token": 8.7e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 8.7e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_aiderpolyglot_percentcorrect_qwen25coder32binstruct_benchmarkleaderboard_247": { "label": "Aider Polyglot", "category": "agentic", "score": 16.4, "scoreText": "16.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-Coder", "exactModelOrSnapshot": "Qwen2.5-Coder-32B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the 32B instruct checkpoint." } } }, { "id": "ovhcloud/ovhcloud/Qwen2.5-VL-72B-Instruct", "slug": "ovhcloud-ovhcloud-qwen2-5-vl-72b-instruct", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "Qwen2.5-VL-72B-Instruct", "displayName": "Qwen2.5-VL-72B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.9099999999999999, "outputUsdPer1MTokens": 0.9099999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.9099999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9.1e-7, "output_cost_per_token": 9.1e-7 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/Qwen2.5-VL-72B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct" }, "rawLitellm": { "input_cost_per_token": 9.1e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 9.1e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "supports_vision": true }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_mmmu_score_qwen25vl32b_officialmodelcard_374": { "label": "MMMU", "category": "multimodal", "score": 70, "scoreText": "70", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mmmupro_score_qwen25vl32b_officialmodelcard_375": { "label": "MMMU-Pro", "category": "multimodal", "score": 49.5, "scoreText": "49.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mmstar_score_qwen25vl32b_officialmodelcard_376": { "label": "MMStar", "category": "multimodal", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mathvista_score_qwen25vl32b_officialmodelcard_377": { "label": "MathVista", "category": "multimodal", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mathvision_score_qwen25vl32b_officialmodelcard_378": { "label": "MathVision", "category": "multimodal", "score": 40, "scoreText": "40.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_ccocr_score_qwen25vl32b_officialmodelcard_379": { "label": "CC-OCR", "category": "multimodal", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_docvqa_score_qwen25vl32b_officialmodelcard_380": { "label": "DocVQA", "category": "multimodal", "score": 94.8, "scoreText": "94.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_infovqa_score_qwen25vl32b_officialmodelcard_381": { "label": "InfoVQA", "category": "multimodal", "score": 83.4, "scoreText": "83.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." } } }, { "id": "ovhcloud/ovhcloud/Qwen3-32B", "slug": "ovhcloud-ovhcloud-qwen3-32b", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "Qwen3-32B", "displayName": "Qwen3-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.22999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 2.3e-7 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/Qwen3-32B", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b" }, "rawLitellm": { "input_cost_per_token": 8e-8, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.3e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true } }, { "id": "ovhcloud/ovhcloud/gpt-oss-120b", "slug": "ovhcloud-ovhcloud-gpt-oss-120b", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 131000, "maxInputTokens": 131000, "maxOutputTokens": 131000, "maxTokens": 131000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "reasoning": true, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/gpt-oss-120b", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b" }, "rawLitellm": { "input_cost_per_token": 8e-8, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 4e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b", "supports_function_calling": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": false }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "ovhcloud/ovhcloud/gpt-oss-20b", "slug": "ovhcloud-ovhcloud-gpt-oss-20b", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "gpt-oss-20b", "displayName": "gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 131000, "maxInputTokens": 131000, "maxOutputTokens": 131000, "maxTokens": 131000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "reasoning": true, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/gpt-oss-20b", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b" }, "rawLitellm": { "input_cost_per_token": 4e-8, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.5e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b", "supports_function_calling": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": false }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "ovhcloud/ovhcloud/llava-v1.6-mistral-7b-hf", "slug": "ovhcloud-ovhcloud-llava-v1-6-mistral-7b-hf", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "llava-v1.6-mistral-7b-hf", "displayName": "llava-v1.6-mistral-7b-hf", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.29, "outputUsdPer1MTokens": 0.29, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.29, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.9e-7, "output_cost_per_token": 2.9e-7 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/llava-v1.6-mistral-7b-hf", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b" }, "rawLitellm": { "input_cost_per_token": 2.9e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.9e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "supports_vision": true }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "ovhcloud/ovhcloud/mamba-codestral-7B-v0.1", "slug": "ovhcloud-ovhcloud-mamba-codestral-7b-v0-1", "provider": "ovhcloud", "providerSlug": "ovhcloud", "name": "mamba-codestral-7B-v0.1", "displayName": "mamba-codestral-7B-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19, "outputUsdPer1MTokens": 0.19, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.9e-7, "output_cost_per_token": 1.9e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "response_schema": true, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "ovhcloud/mamba-codestral-7B-v0.1", "syncedAt": "2026-05-28", "sourceUrl": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1" }, "rawLitellm": { "input_cost_per_token": 1.9e-7, "litellm_provider": "ovhcloud", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.9e-7, "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "palm/palm/chat-bison", "slug": "palm-palm-chat-bison", "provider": "palm", "providerSlug": "palm", "name": "chat-bison", "displayName": "chat-bison", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.125, "outputUsdPer1MTokens": 0.125, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.125, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.25e-7, "output_cost_per_token": 1.25e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "palm/chat-bison", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_token": 1.25e-7, "litellm_provider": "palm", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } }, { "id": "palm/palm/chat-bison-001", "slug": "palm-palm-chat-bison-001", "provider": "palm", "providerSlug": "palm", "name": "chat-bison-001", "displayName": "chat-bison-001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.125, "outputUsdPer1MTokens": 0.125, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.125, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.25e-7, "output_cost_per_token": 1.25e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "palm/chat-bison-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_token": 1.25e-7, "litellm_provider": "palm", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } }, { "id": "palm/palm/text-bison", "slug": "palm-palm-text-bison", "provider": "palm", "providerSlug": "palm", "name": "text-bison", "displayName": "text-bison", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 0.125, "outputUsdPer1MTokens": 0.125, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.125, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.25e-7, "output_cost_per_token": 1.25e-7 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 8192, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "palm/text-bison", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_token": 1.25e-7, "litellm_provider": "palm", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 1.25e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } }, { "id": "palm/palm/text-bison-001", "slug": "palm-palm-text-bison-001", "provider": "palm", "providerSlug": "palm", "name": "text-bison-001", "displayName": "text-bison-001", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 0.125, "outputUsdPer1MTokens": 0.125, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.125, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.25e-7, "output_cost_per_token": 1.25e-7 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 8192, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "palm/text-bison-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_token": 1.25e-7, "litellm_provider": "palm", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 1.25e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } }, { "id": "palm/palm/text-bison-safety-off", "slug": "palm-palm-text-bison-safety-off", "provider": "palm", "providerSlug": "palm", "name": "text-bison-safety-off", "displayName": "text-bison-safety-off", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 0.125, "outputUsdPer1MTokens": 0.125, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.125, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.25e-7, "output_cost_per_token": 1.25e-7 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 8192, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "palm/text-bison-safety-off", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_token": 1.25e-7, "litellm_provider": "palm", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 1.25e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } }, { "id": "palm/palm/text-bison-safety-recitation-off", "slug": "palm-palm-text-bison-safety-recitation-off", "provider": "palm", "providerSlug": "palm", "name": "text-bison-safety-recitation-off", "displayName": "text-bison-safety-recitation-off", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 0.125, "outputUsdPer1MTokens": 0.125, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.125, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.25e-7, "output_cost_per_token": 1.25e-7 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 8192, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "palm/text-bison-safety-recitation-off", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_token": 1.25e-7, "litellm_provider": "palm", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 1.25e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } }, { "id": "parallel_ai/parallel_ai/search", "slug": "parallel_ai-parallel_ai-search", "provider": "parallel_ai", "providerSlug": "parallel_ai", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 4, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.004 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "parallel_ai/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.004, "litellm_provider": "parallel_ai", "mode": "search", "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "parallel_ai/parallel_ai/search-pro", "slug": "parallel_ai-parallel_ai-search-pro", "provider": "parallel_ai", "providerSlug": "parallel_ai", "name": "search-pro", "displayName": "search-pro", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 9, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.009 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "parallel_ai/search-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.009, "litellm_provider": "parallel_ai", "mode": "search", "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "perplexity/perplexity/codellama-34b-instruct", "slug": "perplexity-perplexity-codellama-34b-instruct", "provider": "perplexity", "providerSlug": "perplexity", "name": "codellama-34b-instruct", "displayName": "codellama-34b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 1.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.0000014 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/codellama-34b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.5e-7, "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000014 }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "perplexity/perplexity/codellama-70b-instruct", "slug": "perplexity-perplexity-codellama-70b-instruct", "provider": "perplexity", "providerSlug": "perplexity", "name": "codellama-70b-instruct", "displayName": "codellama-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7, "outputUsdPer1MTokens": 2.8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000028 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2024-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Perplexity changelog says this model would no longer be accessible as of May 14, 2024." }, "source": { "type": "litellm", "litellmKey": "perplexity/codellama-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-7, "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000028, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Perplexity changelog says this model would no longer be accessible as of May 14, 2024." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "perplexity/perplexity/llama-2-70b-chat", "slug": "perplexity-perplexity-llama-2-70b-chat", "provider": "perplexity", "providerSlug": "perplexity", "name": "llama-2-70b-chat", "displayName": "llama-2-70b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7, "outputUsdPer1MTokens": 2.8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000028 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/llama-2-70b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-7, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000028 } }, { "id": "perplexity/perplexity/llama-3.1-70b-instruct", "slug": "perplexity-perplexity-llama-3-1-70b-instruct", "provider": "perplexity", "providerSlug": "perplexity", "name": "llama-3.1-70b-instruct", "displayName": "llama-3.1-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2025-02-22", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Perplexity changelog says this model alias would no longer be accessible as of February 22, 2025." }, "source": { "type": "litellm", "litellmKey": "perplexity/llama-3.1-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000001, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Perplexity changelog says this model alias would no longer be accessible as of February 22, 2025." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "perplexity/perplexity/llama-3.1-8b-instruct", "slug": "perplexity-perplexity-llama-3-1-8b-instruct", "provider": "perplexity", "providerSlug": "perplexity", "name": "llama-3.1-8b-instruct", "displayName": "llama-3.1-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2025-02-22", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Perplexity changelog says this model alias would no longer be accessible as of February 22, 2025." }, "source": { "type": "litellm", "litellmKey": "perplexity/llama-3.1-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-7, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Perplexity changelog says this model alias would no longer be accessible as of February 22, 2025." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "perplexity/perplexity/mistral-7b-instruct", "slug": "perplexity-perplexity-mistral-7b-instruct", "provider": "perplexity", "providerSlug": "perplexity", "name": "mistral-7b-instruct", "displayName": "mistral-7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2024-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Perplexity changelog says this model would no longer be accessible as of May 14, 2024." }, "source": { "type": "litellm", "litellmKey": "perplexity/mistral-7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-8, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-7, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Perplexity changelog says this model would no longer be accessible as of May 14, 2024." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "perplexity/perplexity/mixtral-8x7b-instruct", "slug": "perplexity-perplexity-mixtral-8x7b-instruct", "provider": "perplexity", "providerSlug": "perplexity", "name": "mixtral-8x7b-instruct", "displayName": "mixtral-8x7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/mixtral-8x7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-8, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-7 } }, { "id": "perplexity/perplexity/pplx-70b-chat", "slug": "perplexity-perplexity-pplx-70b-chat", "provider": "perplexity", "providerSlug": "perplexity", "name": "pplx-70b-chat", "displayName": "pplx-70b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7, "outputUsdPer1MTokens": 2.8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000028 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/pplx-70b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-7, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000028 } }, { "id": "perplexity/perplexity/pplx-70b-online", "slug": "perplexity-perplexity-pplx-70b-online", "provider": "perplexity", "providerSlug": "perplexity", "name": "pplx-70b-online", "displayName": "pplx-70b-online", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": 2.8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_request": 0.005, "input_cost_per_token": 0, "output_cost_per_token": 0.0000028 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/pplx-70b-online", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_request": 0.005, "input_cost_per_token": 0, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000028 } }, { "id": "perplexity/perplexity/pplx-7b-chat", "slug": "perplexity-perplexity-pplx-7b-chat", "provider": "perplexity", "providerSlug": "perplexity", "name": "pplx-7b-chat", "displayName": "pplx-7b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2024-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Perplexity changelog says this model would no longer be accessible as of May 14, 2024." }, "source": { "type": "litellm", "litellmKey": "perplexity/pplx-7b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-8, "litellm_provider": "perplexity", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.8e-7, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Perplexity changelog says this model would no longer be accessible as of May 14, 2024." } }, { "id": "perplexity/perplexity/pplx-7b-online", "slug": "perplexity-perplexity-pplx-7b-online", "provider": "perplexity", "providerSlug": "perplexity", "name": "pplx-7b-online", "displayName": "pplx-7b-online", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_request": 0.005, "input_cost_per_token": 0, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2024-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Perplexity changelog says this model would no longer be accessible as of May 14, 2024." }, "source": { "type": "litellm", "litellmKey": "perplexity/pplx-7b-online", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_request": 0.005, "input_cost_per_token": 0, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-7, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Perplexity changelog says this model would no longer be accessible as of May 14, 2024." } }, { "id": "perplexity/perplexity/sonar", "slug": "perplexity-perplexity-sonar", "provider": "perplexity", "providerSlug": "perplexity", "name": "sonar", "displayName": "sonar", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/sonar", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "perplexity", "max_input_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000001, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.005, "search_context_size_medium": 0.008 }, "supports_web_search": true } }, { "id": "perplexity/perplexity/sonar-deep-research", "slug": "perplexity-perplexity-sonar-deep-research", "provider": "perplexity", "providerSlug": "perplexity", "name": "sonar-deep-research", "displayName": "sonar-deep-research", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 3, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "citation_cost_per_token": 0.000002, "input_cost_per_token": 0.000002, "output_cost_per_reasoning_token": 0.000003, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/sonar-deep-research", "syncedAt": "2026-05-28" }, "rawLitellm": { "citation_cost_per_token": 0.000002, "input_cost_per_token": 0.000002, "litellm_provider": "perplexity", "max_input_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_reasoning_token": 0.000003, "output_cost_per_token": 0.000008, "search_context_cost_per_query": { "search_context_size_high": 0.005, "search_context_size_low": 0.005, "search_context_size_medium": 0.005 }, "supports_reasoning": true, "supports_web_search": true } }, { "id": "perplexity/perplexity/sonar-medium-chat", "slug": "perplexity-perplexity-sonar-medium-chat", "provider": "perplexity", "providerSlug": "perplexity", "name": "sonar-medium-chat", "displayName": "sonar-medium-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/sonar-medium-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000018 } }, { "id": "perplexity/perplexity/sonar-medium-online", "slug": "perplexity-perplexity-sonar-medium-online", "provider": "perplexity", "providerSlug": "perplexity", "name": "sonar-medium-online", "displayName": "sonar-medium-online", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_request": 0.005, "input_cost_per_token": 0, "output_cost_per_token": 0.0000018 } }, "limits": { "contextWindow": 12000, "maxInputTokens": 12000, "maxOutputTokens": 12000, "maxTokens": 12000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/sonar-medium-online", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_request": 0.005, "input_cost_per_token": 0, "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, "max_tokens": 12000, "mode": "chat", "output_cost_per_token": 0.0000018 } }, { "id": "perplexity/perplexity/sonar-pro", "slug": "perplexity-perplexity-sonar-pro", "provider": "perplexity", "providerSlug": "perplexity", "name": "sonar-pro", "displayName": "sonar-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 200000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/sonar-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "perplexity", "max_input_tokens": 200000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.006, "search_context_size_medium": 0.01 }, "supports_web_search": true } }, { "id": "perplexity/perplexity/sonar-reasoning", "slug": "perplexity-perplexity-sonar-reasoning", "provider": "perplexity", "providerSlug": "perplexity", "name": "sonar-reasoning", "displayName": "sonar-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2025-12-15", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Perplexity changelog says this model was deprecated and removed as of December 15, 2025." }, "source": { "type": "litellm", "litellmKey": "perplexity/sonar-reasoning", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "perplexity", "max_input_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000005, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.005, "search_context_size_medium": 0.008 }, "supports_reasoning": true, "supports_web_search": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Perplexity changelog says this model was deprecated and removed as of December 15, 2025." } }, { "id": "perplexity/perplexity/sonar-reasoning-pro", "slug": "perplexity-perplexity-sonar-reasoning-pro", "provider": "perplexity", "providerSlug": "perplexity", "name": "sonar-reasoning-pro", "displayName": "sonar-reasoning-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/sonar-reasoning-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "perplexity", "max_input_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000008, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.006, "search_context_size_medium": 0.01 }, "supports_reasoning": true, "supports_web_search": true } }, { "id": "perplexity/perplexity/sonar-small-chat", "slug": "perplexity-perplexity-sonar-small-chat", "provider": "perplexity", "providerSlug": "perplexity", "name": "sonar-small-chat", "displayName": "sonar-small-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/sonar-small-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-8, "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-7 } }, { "id": "perplexity/perplexity/sonar-small-online", "slug": "perplexity-perplexity-sonar-small-online", "provider": "perplexity", "providerSlug": "perplexity", "name": "sonar-small-online", "displayName": "sonar-small-online", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_request": 0.005, "input_cost_per_token": 0, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 12000, "maxInputTokens": 12000, "maxOutputTokens": 12000, "maxTokens": 12000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/sonar-small-online", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_request": 0.005, "input_cost_per_token": 0, "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, "max_tokens": 12000, "mode": "chat", "output_cost_per_token": 2.8e-7 } }, { "id": "publicai/publicai/swiss-ai/apertus-8b-instruct", "slug": "publicai-publicai-swiss-ai-apertus-8b-instruct", "provider": "publicai", "providerSlug": "publicai", "name": "apertus-8b-instruct", "displayName": "apertus-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "publicai/swiss-ai/apertus-8b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.publicai.co/docs" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0, "source": "https://platform.publicai.co/docs", "supports_function_calling": false, "supports_tool_choice": false } }, { "id": "publicai/publicai/swiss-ai/apertus-70b-instruct", "slug": "publicai-publicai-swiss-ai-apertus-70b-instruct", "provider": "publicai", "providerSlug": "publicai", "name": "apertus-70b-instruct", "displayName": "apertus-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "publicai/swiss-ai/apertus-70b-instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.publicai.co/docs" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0, "source": "https://platform.publicai.co/docs", "supports_function_calling": false, "supports_tool_choice": false } }, { "id": "publicai/publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT", "slug": "publicai-publicai-aisingapore-gemma-sea-lion-v4-27b-it", "provider": "publicai", "providerSlug": "publicai", "name": "Gemma-SEA-LION-v4-27B-IT", "displayName": "Gemma-SEA-LION-v4-27B-IT", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.publicai.co/docs" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "publicai/publicai/BSC-LT/salamandra-7b-instruct-tools-16k", "slug": "publicai-publicai-bsc-lt-salamandra-7b-instruct-tools-16k", "provider": "publicai", "providerSlug": "publicai", "name": "salamandra-7b-instruct-tools-16k", "displayName": "salamandra-7b-instruct-tools-16k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "publicai/BSC-LT/salamandra-7b-instruct-tools-16k", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.publicai.co/docs" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "publicai", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "publicai/publicai/BSC-LT/ALIA-40b-instruct_Q8_0", "slug": "publicai-publicai-bsc-lt-alia-40b-instruct_q8_0", "provider": "publicai", "providerSlug": "publicai", "name": "ALIA-40b-instruct_Q8_0", "displayName": "ALIA-40b-instruct_Q8_0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "publicai/BSC-LT/ALIA-40b-instruct_Q8_0", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.publicai.co/docs" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "publicai/publicai/allenai/Olmo-3-7B-Instruct", "slug": "publicai-publicai-allenai-olmo-3-7b-instruct", "provider": "publicai", "providerSlug": "publicai", "name": "Olmo-3-7B-Instruct", "displayName": "Olmo-3-7B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "publicai/allenai/Olmo-3-7B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.publicai.co/docs" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "perplexity/perplexity/preset/fast-search", "slug": "perplexity-perplexity-preset-fast-search", "provider": "perplexity", "providerSlug": "perplexity", "name": "fast-search", "displayName": "fast-search", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "preset": true, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/preset/fast-search", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_preset": true, "supports_function_calling": true } }, { "id": "perplexity/perplexity/preset/pro-search", "slug": "perplexity-perplexity-preset-pro-search", "provider": "perplexity", "providerSlug": "perplexity", "name": "pro-search", "displayName": "pro-search", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "preset": true, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/preset/pro-search", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_preset": true, "supports_function_calling": true } }, { "id": "perplexity/perplexity/preset/deep-research", "slug": "perplexity-perplexity-preset-deep-research", "provider": "perplexity", "providerSlug": "perplexity", "name": "deep-research", "displayName": "deep-research", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "preset": true, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/preset/deep-research", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_preset": true, "supports_function_calling": true } }, { "id": "perplexity/perplexity/preset/advanced-deep-research", "slug": "perplexity-perplexity-preset-advanced-deep-research", "provider": "perplexity", "providerSlug": "perplexity", "name": "advanced-deep-research", "displayName": "advanced-deep-research", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "preset": true, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/preset/advanced-deep-research", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_preset": true, "supports_function_calling": true } }, { "id": "perplexity/perplexity/openai/gpt-5.2", "slug": "perplexity-perplexity-openai-gpt-5-2", "provider": "perplexity", "providerSlug": "perplexity", "name": "gpt-5.2", "displayName": "gpt-5.2", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": true, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/openai/gpt-5.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": true, "supports_function_calling": true }, "benchmarks": { "gdpval_winsorties_gpt52thinking_officiallaunchpost_32": { "label": "GDPval", "category": "other", "score": 70.9, "scoreText": "70.9%", "metric": "wins or ties (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; GPT-5.2 Thinking vs GPT-5.1 Thinking." }, "swebenchpropublic_accuracy_gpt52thinking_officiallaunchpost_33": { "label": "SWE-bench Pro", "category": "coding", "score": 55.6, "scoreText": "55.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; public SWE-Bench Pro score for GPT-5.2 Thinking." }, "aime2025_accuracy_gpt52thinking_officiallaunchpost_34": { "label": "AIME 2025", "category": "reasoning", "score": 100, "scoreText": "100.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-2/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.2", "exactModelOrSnapshot": "GPT-5.2 Thinking", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Detailed benchmarks section; no tools, GPT-5.2 Thinking." } } }, { "id": "perplexity/perplexity/openai/gpt-5.1", "slug": "perplexity-perplexity-openai-gpt-5-1", "provider": "perplexity", "providerSlug": "perplexity", "name": "gpt-5.1", "displayName": "gpt-5.1", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/openai/gpt-5.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true }, "benchmarks": { "swebenchverified_accuracy_gpt51high_officiallaunchpost_29": { "label": "SWE-bench Verified", "category": "coding", "score": 76.3, "scoreText": "76.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "gpqadiamond_accuracy_gpt51high_officiallaunchpost_30": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 88.1, "scoreText": "88.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." }, "tau2benchtelecom_accuracy_gpt51high_officiallaunchpost_31": { "label": "Tau 2-bench Telecom", "category": "agentic", "score": 95.6, "scoreText": "95.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-5-1-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5.1", "exactModelOrSnapshot": "GPT-5.1 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix model-evaluations table comparing GPT-5.1 high vs GPT-5 high." } } }, { "id": "perplexity/perplexity/openai/gpt-5-mini", "slug": "perplexity-perplexity-openai-gpt-5-mini", "provider": "perplexity", "providerSlug": "perplexity", "name": "gpt-5-mini", "displayName": "gpt-5-mini", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/openai/gpt-5-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "perplexity/perplexity/anthropic/claude-opus-4-6", "slug": "perplexity-perplexity-anthropic-claude-opus-4-6", "provider": "perplexity", "providerSlug": "perplexity", "name": "claude-opus-4-6", "displayName": "claude-opus-4-6", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true, "output_config": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/anthropic/claude-opus-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "supports_output_config": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "perplexity/perplexity/anthropic/claude-opus-4-7", "slug": "perplexity-perplexity-anthropic-claude-opus-4-7", "provider": "perplexity", "providerSlug": "perplexity", "name": "claude-opus-4-7", "displayName": "claude-opus-4-7", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true, "output_config": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/anthropic/claude-opus-4-7", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "supports_output_config": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "perplexity/perplexity/anthropic/claude-opus-4-5", "slug": "perplexity-perplexity-anthropic-claude-opus-4-5", "provider": "perplexity", "providerSlug": "perplexity", "name": "claude-opus-4-5", "displayName": "claude-opus-4-5", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/anthropic/claude-opus-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "supports_minimal_reasoning_effort": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "perplexity/perplexity/anthropic/claude-sonnet-4-5", "slug": "perplexity-perplexity-anthropic-claude-sonnet-4-5", "provider": "perplexity", "providerSlug": "perplexity", "name": "claude-sonnet-4-5", "displayName": "claude-sonnet-4-5", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/anthropic/claude-sonnet-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "perplexity/perplexity/anthropic/claude-haiku-4-5", "slug": "perplexity-perplexity-anthropic-claude-haiku-4-5", "provider": "perplexity", "providerSlug": "perplexity", "name": "claude-haiku-4-5", "displayName": "claude-haiku-4-5", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/anthropic/claude-haiku-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "perplexity/perplexity/google/gemini-3-pro-preview", "slug": "perplexity-perplexity-google-gemini-3-pro-preview", "provider": "perplexity", "providerSlug": "perplexity", "name": "gemini-3-pro-preview", "displayName": "gemini-3-pro-preview", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-04-01", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Perplexity changelog says this model was deprecated and removed as of April 1, 2026." }, "source": { "type": "litellm", "litellmKey": "perplexity/google/gemini-3-pro-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Perplexity changelog says this model was deprecated and removed as of April 1, 2026." }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "perplexity/perplexity/google/gemini-3-flash-preview", "slug": "perplexity-perplexity-google-gemini-3-flash-preview", "provider": "perplexity", "providerSlug": "perplexity", "name": "gemini-3-flash-preview", "displayName": "gemini-3-flash-preview", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/google/gemini-3-flash-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true }, "benchmarks": { "swebenchverified_resolved_gemini3flashhighreasoning_benchmarkleaderboard_215": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash (high reasoning)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_gemini3flashpreviewhigh_benchmarkleaderboard_234": { "label": "LiveBench", "category": "general_knowledge", "score": 72.4, "scoreText": "72.40", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Flash", "exactModelOrSnapshot": "Gemini 3 Flash Preview High", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific high-effort variant." } } }, { "id": "perplexity/perplexity/google/gemini-2.5-pro", "slug": "perplexity-perplexity-google-gemini-2-5-pro", "provider": "perplexity", "providerSlug": "perplexity", "name": "gemini-2.5-pro", "displayName": "gemini-2.5-pro", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-04-01", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Perplexity changelog says this model was deprecated and removed as of April 1, 2026." }, "source": { "type": "litellm", "litellmKey": "perplexity/google/gemini-2.5-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Perplexity changelog says this model was deprecated and removed as of April 1, 2026." }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "perplexity/perplexity/google/gemini-2.5-flash", "slug": "perplexity-perplexity-google-gemini-2-5-flash", "provider": "perplexity", "providerSlug": "perplexity", "name": "gemini-2.5-flash", "displayName": "gemini-2.5-flash", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-03-20", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Perplexity changelog says this model was deprecated and removed as of March 20, 2026." }, "source": { "type": "litellm", "litellmKey": "perplexity/google/gemini-2.5-flash", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.perplexity.ai/docs/resources/changelog" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Perplexity changelog says this model was deprecated and removed as of March 20, 2026." } }, { "id": "perplexity/perplexity/xai/grok-4-1-fast-non-reasoning", "slug": "perplexity-perplexity-xai-grok-4-1-fast-non-reasoning", "provider": "perplexity", "providerSlug": "perplexity", "name": "grok-4-1-fast-non-reasoning", "displayName": "grok-4-1-fast-non-reasoning", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/xai/grok-4-1-fast-non-reasoning", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "perplexity/perplexity/perplexity/sonar", "slug": "perplexity-perplexity-perplexity-sonar", "provider": "perplexity", "providerSlug": "perplexity", "name": "sonar", "displayName": "sonar", "mode": "responses", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "web_search": true, "reasoning": false, "function_calling": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/perplexity/sonar", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true } }, { "id": "perplexity/perplexity/pplx-embed-v1-0.6b", "slug": "perplexity-perplexity-pplx-embed-v1-0-6b", "provider": "perplexity", "providerSlug": "perplexity", "name": "pplx-embed-v1-0.6b", "displayName": "pplx-embed-v1-0.6b", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.004, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.004, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-9, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": null, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1024, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/pplx-embed-v1-0.6b", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.perplexity.ai/docs/embeddings/quickstart" }, "rawLitellm": { "input_cost_per_token": 4e-9, "litellm_provider": "perplexity", "max_input_tokens": 32768, "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1024, "source": "https://docs.perplexity.ai/docs/embeddings/quickstart" } }, { "id": "perplexity/perplexity/pplx-embed-v1-4b", "slug": "perplexity-perplexity-pplx-embed-v1-4b", "provider": "perplexity", "providerSlug": "perplexity", "name": "pplx-embed-v1-4b", "displayName": "pplx-embed-v1-4b", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.03, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.03, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": null, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 2560, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "perplexity/pplx-embed-v1-4b", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.perplexity.ai/docs/embeddings/quickstart" }, "rawLitellm": { "input_cost_per_token": 3e-8, "litellm_provider": "perplexity", "max_input_tokens": 32768, "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 2560, "source": "https://docs.perplexity.ai/docs/embeddings/quickstart" } }, { "id": "publicai/publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT", "slug": "publicai-publicai-aisingapore-qwen-sea-lion-v4-32b-it", "provider": "publicai", "providerSlug": "publicai", "name": "Qwen-SEA-LION-v4-32B-IT", "displayName": "Qwen-SEA-LION-v4-32B-IT", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.publicai.co/docs" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "publicai/publicai/allenai/Olmo-3-7B-Think", "slug": "publicai-publicai-allenai-olmo-3-7b-think", "provider": "publicai", "providerSlug": "publicai", "name": "Olmo-3-7B-Think", "displayName": "Olmo-3-7B-Think", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "publicai/allenai/Olmo-3-7B-Think", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.publicai.co/docs" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true } }, { "id": "publicai/publicai/allenai/Olmo-3-32B-Think", "slug": "publicai-publicai-allenai-olmo-3-32b-think", "provider": "publicai", "providerSlug": "publicai", "name": "Olmo-3-32B-Think", "displayName": "Olmo-3-32B-Think", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "publicai/allenai/Olmo-3-32B-Think", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.publicai.co/docs" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true } }, { "id": "bedrock_converse/qwen.qwen3-coder-480b-a35b-v1:0", "slug": "bedrock_converse-qwen-qwen3-coder-480b-a35b-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "qwen.qwen3-coder-480b-a35b-v1:0", "displayName": "qwen.qwen3-coder-480b-a35b-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 0.0000018 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "native_structured_output": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "qwen.qwen3-coder-480b-a35b-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 262000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000018, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html" ], "manual_model_modalities_note": "Bedrock Converse exact Qwen route id from official docs" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock_converse/qwen.qwen3-235b-a22b-2507-v1:0", "slug": "bedrock_converse-qwen-qwen3-235b-a22b-2507-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "qwen.qwen3-235b-a22b-2507-v1:0", "displayName": "qwen.qwen3-235b-a22b-2507-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 262144, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "native_structured_output": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "qwen.qwen3-235b-a22b-2507-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-7, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" ], "manual_model_modalities_note": "Bedrock Converse exact Qwen route id from official docs" } }, { "id": "bedrock_converse/qwen.qwen3-coder-30b-a3b-v1:0", "slug": "bedrock_converse-qwen-qwen3-coder-30b-a3b-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "qwen.qwen3-coder-30b-a3b-v1:0", "displayName": "qwen.qwen3-coder-30b-a3b-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 262144, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "native_structured_output": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "qwen.qwen3-coder-30b-a3b-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "bedrock_converse/qwen.qwen3-32b-v1:0", "slug": "bedrock_converse-qwen-qwen3-32b-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "qwen.qwen3-32b-v1:0", "displayName": "qwen.qwen3-32b-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 131072, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "native_structured_output": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "qwen.qwen3-32b-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true } }, { "id": "bedrock_converse/qwen.qwen3-next-80b-a3b", "slug": "bedrock_converse-qwen-qwen3-next-80b-a3b", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "qwen.qwen3-next-80b-a3b", "displayName": "qwen.qwen3-next-80b-a3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "native_structured_output": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "qwen.qwen3-next-80b-a3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "bedrock_converse/qwen.qwen3-vl-235b-a22b", "slug": "bedrock_converse-qwen-qwen3-vl-235b-a22b", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "qwen.qwen3-vl-235b-a22b", "displayName": "qwen.qwen3-vl-235b-a22b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.53, "outputUsdPer1MTokens": 2.66, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.53, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.3e-7, "output_cost_per_token": 0.00000266 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "qwen.qwen3-vl-235b-a22b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5.3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000266, "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-vl-235b-a22b.html" ], "manual_model_modalities_note": "Bedrock Converse exact Qwen route id from official docs" } }, { "id": "bedrock_converse/qwen.qwen3-coder-next", "slug": "bedrock_converse-qwen-qwen3-coder-next", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "qwen.qwen3-coder-next", "displayName": "qwen.qwen3-coder-next", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 262144, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "qwen.qwen3-coder-next", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "reducto/reducto/parse-legacy", "slug": "reducto-reducto-parse-legacy", "provider": "reducto", "providerSlug": "reducto", "name": "parse-legacy", "displayName": "parse-legacy", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "ocr_cost_per_credit": 0.015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [ "/v1/ocr" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "reducto/parse-legacy", "syncedAt": "2026-05-28", "sourceUrl": "https://reducto.ai/pricing" }, "rawLitellm": { "litellm_provider": "reducto", "mode": "ocr", "ocr_cost_per_credit": 0.015, "source": "https://reducto.ai/pricing", "supported_endpoints": [ "/v1/ocr" ], "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "reducto/reducto/parse-v3", "slug": "reducto-reducto-parse-v3", "provider": "reducto", "providerSlug": "reducto", "name": "parse-v3", "displayName": "parse-v3", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "ocr_cost_per_credit": 0.015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [ "/v1/ocr" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "reducto/parse-v3", "syncedAt": "2026-05-28", "sourceUrl": "https://reducto.ai/pricing" }, "rawLitellm": { "litellm_provider": "reducto", "mode": "ocr", "ocr_cost_per_credit": 0.015, "source": "https://reducto.ai/pricing", "supported_endpoints": [ "/v1/ocr" ], "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "recraft/recraft/recraftv2", "slug": "recraft-recraft-recraftv2", "provider": "recraft", "providerSlug": "recraft", "name": "recraftv2", "displayName": "recraftv2", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 22000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.022 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "recraft/recraftv2", "syncedAt": "2026-05-28", "sourceUrl": "https://www.recraft.ai/docs#pricing" }, "rawLitellm": { "litellm_provider": "recraft", "mode": "image_generation", "output_cost_per_image": 0.022, "source": "https://www.recraft.ai/docs#pricing", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "recraft/recraft/recraftv3", "slug": "recraft-recraft-recraftv3", "provider": "recraft", "providerSlug": "recraft", "name": "recraftv3", "displayName": "recraftv3", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "recraft/recraftv3", "syncedAt": "2026-05-28", "sourceUrl": "https://www.recraft.ai/docs#pricing" }, "rawLitellm": { "litellm_provider": "recraft", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://www.recraft.ai/docs#pricing", "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "replicate/replicate/meta/llama-2-13b", "slug": "replicate-replicate-meta-llama-2-13b", "provider": "replicate", "providerSlug": "replicate", "name": "llama-2-13b", "displayName": "llama-2-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/meta/llama-2-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/meta/llama-2-13b" ], "manual_model_modalities_note": "Replicate exact route id from official model page." } }, { "id": "replicate/replicate/meta/llama-2-13b-chat", "slug": "replicate-replicate-meta-llama-2-13b-chat", "provider": "replicate", "providerSlug": "replicate", "name": "llama-2-13b-chat", "displayName": "llama-2-13b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/meta/llama-2-13b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/meta/llama-2-13b-chat" ], "manual_model_modalities_note": "Replicate exact route id from official model page." } }, { "id": "replicate/replicate/meta/llama-2-70b", "slug": "replicate-replicate-meta-llama-2-70b", "provider": "replicate", "providerSlug": "replicate", "name": "llama-2-70b", "displayName": "llama-2-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.65, "outputUsdPer1MTokens": 2.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000275 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/meta/llama-2-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6.5e-7, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000275, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/meta/llama-2-70b" ], "manual_model_modalities_note": "Replicate exact route id from official model page." } }, { "id": "replicate/replicate/meta/llama-2-70b-chat", "slug": "replicate-replicate-meta-llama-2-70b-chat", "provider": "replicate", "providerSlug": "replicate", "name": "llama-2-70b-chat", "displayName": "llama-2-70b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.65, "outputUsdPer1MTokens": 2.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000275 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/meta/llama-2-70b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6.5e-7, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000275, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/meta/llama-2-70b-chat" ], "manual_model_modalities_note": "Replicate exact route id from official model page." } }, { "id": "replicate/replicate/meta/llama-2-7b", "slug": "replicate-replicate-meta-llama-2-7b", "provider": "replicate", "providerSlug": "replicate", "name": "llama-2-7b", "displayName": "llama-2-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/meta/llama-2-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/meta/llama-2-7b" ], "manual_model_modalities_note": "Replicate exact route id from official model page." } }, { "id": "replicate/replicate/meta/llama-2-7b-chat", "slug": "replicate-replicate-meta-llama-2-7b-chat", "provider": "replicate", "providerSlug": "replicate", "name": "llama-2-7b-chat", "displayName": "llama-2-7b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/meta/llama-2-7b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/meta/llama-2-7b-chat" ], "manual_model_modalities_note": "Replicate exact route id from official model page." } }, { "id": "replicate/replicate/meta/llama-3-70b", "slug": "replicate-replicate-meta-llama-3-70b", "provider": "replicate", "providerSlug": "replicate", "name": "llama-3-70b", "displayName": "llama-3-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.65, "outputUsdPer1MTokens": 2.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000275 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/meta/llama-3-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6.5e-7, "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000275, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/meta/meta-llama-3-70b/readme", "https://replicate.com/meta/meta-llama-3-70b" ], "manual_model_modalities_note": "Replicate exact route id from official model docs." } }, { "id": "replicate/replicate/meta/llama-3-70b-instruct", "slug": "replicate-replicate-meta-llama-3-70b-instruct", "provider": "replicate", "providerSlug": "replicate", "name": "llama-3-70b-instruct", "displayName": "llama-3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.65, "outputUsdPer1MTokens": 2.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000275 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/meta/llama-3-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6.5e-7, "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000275, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/meta/meta-llama-3-70b-instruct/readme", "https://replicate.com/meta/meta-llama-3-70b-instruct" ], "manual_model_modalities_note": "Replicate exact route id from official model docs." } }, { "id": "replicate/replicate/meta/llama-3-8b", "slug": "replicate-replicate-meta-llama-3-8b", "provider": "replicate", "providerSlug": "replicate", "name": "llama-3-8b", "displayName": "llama-3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 8086, "maxInputTokens": 8086, "maxOutputTokens": 8086, "maxTokens": 8086, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/meta/llama-3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, "max_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/meta/meta-llama-3-8b", "https://replicate.com/meta/meta-llama-3-8b/readme" ], "manual_model_modalities_note": "Replicate exact route id from official model docs." } }, { "id": "replicate/replicate/meta/llama-3-8b-instruct", "slug": "replicate-replicate-meta-llama-3-8b-instruct", "provider": "replicate", "providerSlug": "replicate", "name": "llama-3-8b-instruct", "displayName": "llama-3-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 8086, "maxInputTokens": 8086, "maxOutputTokens": 8086, "maxTokens": 8086, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/meta/llama-3-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, "max_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/meta/meta-llama-3-8b-instruct", "https://replicate.com/meta/meta-llama-3-8b-instruct/readme" ], "manual_model_modalities_note": "Replicate exact route id from official model docs." } }, { "id": "replicate/replicate/mistralai/mistral-7b-instruct-v0.2", "slug": "replicate-replicate-mistralai-mistral-7b-instruct-v0-2", "provider": "replicate", "providerSlug": "replicate", "name": "mistral-7b-instruct-v0.2", "displayName": "mistral-7b-instruct-v0.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/mistralai/mistral-7b-instruct-v0.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/blog/run-mistral-7b-with-api/", "https://docs.mistral.ai/models/model-cards/mistral-7b-0-2", "https://docs.mistral.ai/api/endpoint/models" ], "manual_model_modalities_note": "Replicate exact route id from official docs." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "replicate/replicate/mistralai/mistral-7b-v0.1", "slug": "replicate-replicate-mistralai-mistral-7b-v0-1", "provider": "replicate", "providerSlug": "replicate", "name": "mistral-7b-v0.1", "displayName": "mistral-7b-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/mistralai/mistral-7b-v0.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/mistralai/mistral-7b-v0.1/api/learn-more", "https://docs.mistral.ai/models/model-cards/mistral-7b-0-1", "https://docs.mistral.ai/api/endpoint/models" ], "manual_model_modalities_note": "Replicate exact route id from official docs." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "replicate/replicate/mistralai/mixtral-8x7b-instruct-v0.1", "slug": "replicate-replicate-mistralai-mixtral-8x7b-instruct-v0-1", "provider": "replicate", "providerSlug": "replicate", "name": "mixtral-8x7b-instruct-v0.1", "displayName": "mixtral-8x7b-instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/mistralai/mixtral-8x7b-instruct-v0.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000001, "supports_tool_choice": true } }, { "id": "replicate/replicate/openai/gpt-5", "slug": "replicate-replicate-openai-gpt-5", "provider": "replicate", "providerSlug": "replicate", "name": "gpt-5", "displayName": "gpt-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/gpt-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/gpt-5" ], "manual_model_modalities_note": "Replicate exact route id from official model page." }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "replicate/replicateopenai/gpt-oss-20b", "slug": "replicate-replicateopenai-gpt-oss-20b", "provider": "replicate", "providerSlug": "replicate", "name": "gpt-oss-20b", "displayName": "gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.36, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 3.6e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicateopenai/gpt-oss-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9e-8, "output_cost_per_token": 3.6e-7, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/gpt-oss-20b", "https://huggingface.co/openai/gpt-oss-20b" ], "manual_model_modalities_note": "Replicate exact route id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "replicate/replicate/anthropic/claude-4.5-haiku", "slug": "replicate-replicate-anthropic-claude-4-5-haiku", "provider": "replicate", "providerSlug": "replicate", "name": "claude-4.5-haiku", "displayName": "claude-4.5-haiku", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true, "prompt_caching": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/anthropic/claude-4.5-haiku", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/anthropic/claude-4.5-haiku" ], "manual_model_modalities_note": "Replicate exact route id from official model page." }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "replicate/replicate/ibm-granite/granite-3.3-8b-instruct", "slug": "replicate-replicate-ibm-granite-granite-3-3-8b-instruct", "provider": "replicate", "providerSlug": "replicate", "name": "granite-3.3-8b-instruct", "displayName": "granite-3.3-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.03, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.03, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-8, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/ibm-granite/granite-3.3-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-8, "output_cost_per_token": 2.5e-7, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/ibm-granite/granite-3.3-8b-instruct" ], "manual_model_modalities_note": "Replicate exact route id from official model page." } }, { "id": "replicate/replicate/openai/gpt-4o", "slug": "replicate-replicate-openai-gpt-4o", "provider": "replicate", "providerSlug": "replicate", "name": "gpt-4o", "displayName": "gpt-4o", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true, "audio_input": true, "audio_output": true } }, "modalities": { "supported": [ "audio", "image", "text" ], "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/gpt-4o", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_audio_input": true, "supports_audio_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/gpt-4o" ], "manual_model_modalities_note": "Replicate exact route id from official model page." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "replicate/replicate/openai/o4-mini", "slug": "replicate-replicate-openai-o4-mini", "provider": "replicate", "providerSlug": "replicate", "name": "o4-mini", "displayName": "o4-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 4, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000004, "output_cost_per_reasoning_token": 0.000004 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/o4-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000004, "output_cost_per_reasoning_token": 0.000004, "litellm_provider": "replicate", "mode": "chat", "supports_reasoning": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/o4-mini", "https://replicate.com/openai/o4-mini/versions/c54e0167f97f481a306985bc38bba4d9c6664c13e99cf4d49d62e7af25542677/api" ], "manual_model_modalities_note": "Replicate exact route id from official schema." }, "benchmarks": { "aime2025_accuracy_openaio4minihigh_officiallaunchpost_15": { "label": "AIME 2025", "category": "reasoning", "score": 92.7, "scoreText": "92.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio4minihigh_officiallaunchpost_16": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 81.4, "scoreText": "81.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio4minihigh_officiallaunchpost_17": { "label": "SWE-bench Verified", "category": "coding", "score": 68.1, "scoreText": "68.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "replicate/replicate/openai/o1-mini", "slug": "replicate-replicate-openai-o1-mini", "provider": "replicate", "providerSlug": "replicate", "name": "o1-mini", "displayName": "o1-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 4.4, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "output_cost_per_reasoning_token": 0.0000044 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/o1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "output_cost_per_reasoning_token": 0.0000044, "litellm_provider": "replicate", "mode": "chat", "supports_reasoning": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/o1-mini", "https://replicate.com/openai/o1-mini/versions/afb63ac5dc420133173c4e864bb7c124404281d4dedc6b23776c80dd508213e3/api" ], "manual_model_modalities_note": "Replicate exact route id from official schema." } }, { "id": "replicate/replicate/openai/o1", "slug": "replicate-replicate-openai-o1", "provider": "replicate", "providerSlug": "replicate", "name": "openai", "displayName": "openai", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 60, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "output_cost_per_reasoning_token": 0.00006 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/o1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "output_cost_per_reasoning_token": 0.00006, "litellm_provider": "replicate", "mode": "chat", "supports_reasoning": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/o1", "https://replicate.com/openai/o1/versions/23162e89bcebe497ddbc1bee01fedcea7207c0ff19f8ebdd8c0b13372e02f364/api" ], "manual_model_modalities_note": "Replicate exact route id from official schema." } }, { "id": "replicate/replicate/openai/gpt-4o-mini", "slug": "replicate-replicate-openai-gpt-4o-mini", "provider": "replicate", "providerSlug": "replicate", "name": "gpt-4o-mini", "displayName": "gpt-4o-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/gpt-4o-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/gpt-4o-mini", "https://replicate.com/openai/gpt-4o-mini/api/schema" ], "manual_model_modalities_note": "Replicate exact route id from official schema." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "replicate/replicate/qwen/qwen3-235b-a22b-instruct-2507", "slug": "replicate-replicate-qwen-qwen3-235b-a22b-instruct-2507", "provider": "replicate", "providerSlug": "replicate", "name": "qwen3-235b-a22b-instruct-2507", "displayName": "qwen3-235b-a22b-instruct-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.26399999999999996, "outputUsdPer1MTokens": 1.06, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.26399999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.64e-7, "output_cost_per_token": 0.00000106 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/qwen/qwen3-235b-a22b-instruct-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.64e-7, "output_cost_per_token": 0.00000106, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/qwen/qwen3-235b-a22b-instruct-2507", "https://replicate.com/qwen/qwen3-235b-a22b-instruct-2507/versions/ed6cfb0378aae58d3cae29395120c87477eb4574b7f82ac517ff491c9ae2b768/api" ], "manual_model_modalities_note": "Replicate exact route id from official schema." } }, { "id": "replicate/replicate/anthropic/claude-4-sonnet", "slug": "replicate-replicate-anthropic-claude-4-sonnet", "provider": "replicate", "providerSlug": "replicate", "name": "claude-4-sonnet", "displayName": "claude-4-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true, "prompt_caching": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/anthropic/claude-4-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/anthropic/claude-4-sonnet", "https://replicate.com/anthropic/claude-4-sonnet/api/schema" ], "manual_model_modalities_note": "Replicate exact route id from official schema." } }, { "id": "replicate/replicate/deepseek-ai/deepseek-v3", "slug": "replicate-replicate-deepseek-ai-deepseek-v3", "provider": "replicate", "providerSlug": "replicate", "name": "deepseek-v3", "displayName": "deepseek-v3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.4500000000000002, "outputUsdPer1MTokens": 1.4500000000000002, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.4500000000000002, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000145, "output_cost_per_token": 0.00000145 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65536, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/deepseek-ai/deepseek-v3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000145, "output_cost_per_token": 0.00000145, "litellm_provider": "replicate", "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "supports_function_calling": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/deepseek-ai/deepseek-v3", "https://replicate.com/deepseek-ai/deepseek-v3/api" ], "manual_model_modalities_note": "Replicate exact route id from official docs." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "replicate/replicate/anthropic/claude-3.7-sonnet", "slug": "replicate-replicate-anthropic-claude-3-7-sonnet", "provider": "replicate", "providerSlug": "replicate", "name": "claude-3.7-sonnet", "displayName": "claude-3.7-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true, "prompt_caching": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/anthropic/claude-3.7-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/anthropic/claude-3.7-sonnet/api/schema", "https://replicate.com/anthropic/claude-3.7-sonnet/api/learn-more" ], "manual_model_modalities_note": "Replicate exact route id from official schema." }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "replicate/replicate/anthropic/claude-3.5-haiku", "slug": "replicate-replicate-anthropic-claude-3-5-haiku", "provider": "replicate", "providerSlug": "replicate", "name": "claude-3.5-haiku", "displayName": "claude-3.5-haiku", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true, "prompt_caching": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/anthropic/claude-3.5-haiku", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/anthropic/claude-3.5-haiku", "https://replicate.com/anthropic/claude-3.5-haiku/api/schema" ], "manual_model_modalities_note": "Replicate exact route id from official schema." }, "benchmarks": { "aidercodeeditingleaderboard_score_claude35haiku20241022_benchmarkleaderboard_68": { "label": "Aider Code Editing", "category": "coding", "score": 75.2, "scoreText": "75.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Haiku", "exactModelOrSnapshot": "claude-3-5-haiku-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." } } }, { "id": "replicate/replicate/anthropic/claude-3.5-sonnet", "slug": "replicate-replicate-anthropic-claude-3-5-sonnet", "provider": "replicate", "providerSlug": "replicate", "name": "claude-3.5-sonnet", "displayName": "claude-3.5-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.75, "outputUsdPer1MTokens": 18.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000375, "output_cost_per_token": 0.00001875 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true, "prompt_caching": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/anthropic/claude-3.5-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000375, "output_cost_per_token": 0.00001875, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/anthropic/claude-3.5-sonnet/api/schema" ], "manual_model_modalities_note": "Replicate exact route id from official schema." }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "replicate/replicate/google/gemini-3-pro", "slug": "replicate-replicate-google-gemini-3-pro", "provider": "replicate", "providerSlug": "replicate", "name": "gemini-3-pro", "displayName": "gemini-3-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/google/gemini-3-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/google/gemini-3-pro", "https://ai.google.dev/gemini-api/docs/models" ], "manual_model_modalities_note": "Replicate exact route id from official docs." }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "replicate/replicate/anthropic/claude-4.5-sonnet", "slug": "replicate-replicate-anthropic-claude-4-5-sonnet", "provider": "replicate", "providerSlug": "replicate", "name": "claude-4.5-sonnet", "displayName": "claude-4.5-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true, "prompt_caching": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/anthropic/claude-4.5-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/anthropic/claude-4.5-sonnet" ], "manual_model_modalities_note": "Replicate exact route id from official model page." } }, { "id": "replicate/replicate/openai/gpt-4.1", "slug": "replicate-replicate-openai-gpt-4-1", "provider": "replicate", "providerSlug": "replicate", "name": "gpt-4.1", "displayName": "gpt-4.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/gpt-4.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/gpt-4.1" ], "manual_model_modalities_note": "Replicate exact route id from official model page." }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "replicate/replicate/openai/gpt-4.1-nano", "slug": "replicate-replicate-openai-gpt-4-1-nano", "provider": "replicate", "providerSlug": "replicate", "name": "gpt-4.1-nano", "displayName": "gpt-4.1-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/gpt-4.1-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/gpt-4.1-nano" ], "manual_model_modalities_note": "Replicate exact route id from official model page." }, "benchmarks": { "aime24_accuracy_gpt41nano_officiallaunchpost_6": { "label": "AIME 2024", "category": "reasoning", "score": 29.4, "scoreText": "29.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-nano", "exactModelOrSnapshot": "GPT-4.1 nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Academic-knowledge appendix comparison row for the nano model." }, "mmlu_accuracy_gpt41nano_officiallaunchpost_258": { "label": "MMLU", "category": "general_knowledge", "score": 80.1, "scoreText": "80.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the narrative and table." }, "gpqa_accuracy_gpt41nano_officiallaunchpost_259": { "label": "GPQA", "category": "reasoning", "score": 50.3, "scoreText": "50.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." }, "aiderpolyglotcoding_passrate_gpt41nano_officiallaunchpost_260": { "label": "Aider Polyglot", "category": "coding", "score": 9.8, "scoreText": "9.8%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." } } }, { "id": "replicate/replicate/openai/gpt-4.1-mini", "slug": "replicate-replicate-openai-gpt-4-1-mini", "provider": "replicate", "providerSlug": "replicate", "name": "gpt-4.1-mini", "displayName": "gpt-4.1-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/gpt-4.1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/gpt-4.1-mini" ], "manual_model_modalities_note": "Replicate exact route id from official model page." }, "benchmarks": { "swebenchverified_accuracy_gpt41mini_officiallaunchpost_5": { "label": "SWE-bench Verified", "category": "coding", "score": 23.6, "scoreText": "23.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-mini", "exactModelOrSnapshot": "GPT-4.1 mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table for the GPT-4.1 family." } } }, { "id": "replicate/replicate/openai/gpt-5-nano", "slug": "replicate-replicate-openai-gpt-5-nano", "provider": "replicate", "providerSlug": "replicate", "name": "gpt-5-nano", "displayName": "gpt-5-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/gpt-5-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/gpt-5-nano" ], "manual_model_modalities_note": "Replicate exact route id from official model page." }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "aime2025_accuracy_gpt5nanohigh_officiallaunchpost_28": { "label": "AIME 2025", "category": "reasoning", "score": 85.2, "scoreText": "85.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-nano", "exactModelOrSnapshot": "GPT-5 nano (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." } } }, { "id": "replicate/replicate/openai/gpt-5-mini", "slug": "replicate-replicate-openai-gpt-5-mini", "provider": "replicate", "providerSlug": "replicate", "name": "gpt-5-mini", "displayName": "gpt-5-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/gpt-5-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/gpt-5-mini", "https://replicate.com/openai/gpt-5-mini/api/schema" ], "manual_model_modalities_note": "Replicate exact route id from official schema." }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." }, "swebenchverified_accuracy_gpt5minihigh_officiallaunchpost_26": { "label": "SWE-bench Verified", "category": "coding", "score": 71, "scoreText": "71.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "gpqadiamond_accuracy_gpt5minihigh_officiallaunchpost_27": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 82.3, "scoreText": "82.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5-mini", "exactModelOrSnapshot": "GPT-5 mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "swebenchverified_resolved_gpt5mini_benchmarkleaderboard_219": { "label": "SWE-bench Verified", "category": "coding", "score": 56.2, "scoreText": "56.20%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5 Mini", "exactModelOrSnapshot": "GPT-5 Mini", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." } } }, { "id": "replicate/replicate/google/gemini-2.5-flash", "slug": "replicate-replicate-google-gemini-2-5-flash", "provider": "replicate", "providerSlug": "replicate", "name": "gemini-2.5-flash", "displayName": "gemini-2.5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true, "system_messages": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/google/gemini-2.5-flash", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.0000025, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/google/gemini-2.5-flash", "https://replicate.com/google/gemini-2.5-flash/readme" ], "manual_model_modalities_note": "Replicate exact route id from official docs." } }, { "id": "replicate/replicate/openai/gpt-oss-120b", "slug": "replicate-replicate-openai-gpt-oss-120b", "provider": "replicate", "providerSlug": "replicate", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/openai/gpt-oss-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 7.2e-7, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/openai/gpt-oss-120b", "https://replicate.com/openai/gpt-oss-120b/api/schema" ], "manual_model_modalities_note": "Replicate exact route id from official schema." }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "replicate/replicate/deepseek-ai/deepseek-v3.1", "slug": "replicate-replicate-deepseek-ai-deepseek-v3-1", "provider": "replicate", "providerSlug": "replicate", "name": "deepseek-v3.1", "displayName": "deepseek-v3.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6719999999999999, "outputUsdPer1MTokens": 2.016, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6719999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.72e-7, "output_cost_per_token": 0.000002016 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/deepseek-ai/deepseek-v3.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6.72e-7, "output_cost_per_token": 0.000002016, "litellm_provider": "replicate", "mode": "chat", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/deepseek-ai/deepseek-v3.1", "https://replicate.com/deepseek-ai/deepseek-v3.1/versions/bfee48c44db02fe29ad3b47e60b7b4a16a1f4e6fcca4d97ace2f3cf68a52ed10/api" ], "manual_model_modalities_note": "Replicate exact route id from official schema." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "replicate/replicate/xai/grok-4", "slug": "replicate-replicate-xai-grok-4", "provider": "replicate", "providerSlug": "replicate", "name": "grok-4", "displayName": "grok-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 7.199999999999999, "outputUsdPer1MTokens": 36, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 7.199999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000072, "output_cost_per_token": 0.000036 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/xai/grok-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000072, "output_cost_per_token": 0.000036, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/xai/grok-4", "https://replicate.com/xai/grok-4/versions/6931a60a30aca358f75d738ce255b6f691a3bc96ec1d8e2affce58a3852b1ec2/api" ], "manual_model_modalities_note": "Replicate exact route id from official schema." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "replicate/replicate/deepseek-ai/deepseek-r1", "slug": "replicate-replicate-deepseek-ai-deepseek-r1", "provider": "replicate", "providerSlug": "replicate", "name": "deepseek-r1", "displayName": "deepseek-r1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.75, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 10, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000375, "output_cost_per_token": 0.00001, "output_cost_per_reasoning_token": 0.00001 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65536, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "replicate/deepseek-ai/deepseek-r1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000375, "output_cost_per_token": 0.00001, "output_cost_per_reasoning_token": 0.00001, "litellm_provider": "replicate", "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "supports_reasoning": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://replicate.com/deepseek-ai/deepseek-r1", "https://replicate.com/deepseek-ai/deepseek-r1/versions/d0426501ce0499770ac3d3494e9f3c7c03f9b10e569212f6148a4fd337ec3ece/api" ], "manual_model_modalities_note": "Replicate exact route id from official schema." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "cohere/rerank-english-v2.0", "slug": "cohere-rerank-english-v2-0", "provider": "Cohere", "providerSlug": "cohere", "name": "rerank-english-v2.0", "displayName": "rerank-english-v2.0", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 2048, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2024-12-02", "shutdownDate": "2025-04-30", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.cohere.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "rerank-english-v2.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.cohere.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "cohere/rerank-english-v3.0", "slug": "cohere-rerank-english-v3-0", "provider": "Cohere", "providerSlug": "cohere", "name": "rerank-english-v3.0", "displayName": "rerank-english-v3.0", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 2048, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "rerank-english-v3.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "cohere/rerank-multilingual-v2.0", "slug": "cohere-rerank-multilingual-v2-0", "provider": "Cohere", "providerSlug": "cohere", "name": "rerank-multilingual-v2.0", "displayName": "rerank-multilingual-v2.0", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 2048, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2024-12-02", "shutdownDate": "2025-04-30", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.cohere.com/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "rerank-multilingual-v2.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.cohere.com/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null } }, { "id": "cohere/rerank-multilingual-v3.0", "slug": "cohere-rerank-multilingual-v3-0", "provider": "Cohere", "providerSlug": "cohere", "name": "rerank-multilingual-v3.0", "displayName": "rerank-multilingual-v3.0", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 2048, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "rerank-multilingual-v3.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "cohere/rerank-v3.5", "slug": "cohere-rerank-v3-5", "provider": "Cohere", "providerSlug": "cohere", "name": "rerank-v3.5", "displayName": "rerank-v3.5", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 2, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 2048, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "rerank-v3.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.002, "input_cost_per_token": 0, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_query_tokens": 2048, "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "nvidia_nim/nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3", "slug": "nvidia_nim-nvidia_nim-nvidia-nv-rerankqa-mistral-4b-v3", "provider": "nvidia_nim", "providerSlug": "nvidia_nim", "name": "nv-rerankqa-mistral-4b-v3", "displayName": "nv-rerankqa-mistral-4b-v3", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0, "input_cost_per_token": 0, "litellm_provider": "nvidia_nim", "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "nvidia_nim/nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2", "slug": "nvidia_nim-nvidia_nim-nvidia-llama-3_2-nv-rerankqa-1b-v2", "provider": "nvidia_nim", "providerSlug": "nvidia_nim", "name": "llama-3_2-nv-rerankqa-1b-v2", "displayName": "llama-3_2-nv-rerankqa-1b-v2", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0, "input_cost_per_token": 0, "litellm_provider": "nvidia_nim", "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "nvidia_nim/nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2", "slug": "nvidia_nim-nvidia_nim-ranking-nvidia-llama-3-2-nv-rerankqa-1b-v2", "provider": "nvidia_nim", "providerSlug": "nvidia_nim", "name": "llama-3.2-nv-rerankqa-1b-v2", "displayName": "llama-3.2-nv-rerankqa-1b-v2", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0, "input_cost_per_token": 0, "litellm_provider": "nvidia_nim", "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "sagemaker/sagemaker/meta-textgeneration-llama-2-13b", "slug": "sagemaker-sagemaker-meta-textgeneration-llama-2-13b", "provider": "sagemaker", "providerSlug": "sagemaker", "name": "meta-textgeneration-llama-2-13b", "displayName": "meta-textgeneration-llama-2-13b", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sagemaker/meta-textgeneration-llama-2-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0 } }, { "id": "sagemaker/sagemaker/meta-textgeneration-llama-2-13b-f", "slug": "sagemaker-sagemaker-meta-textgeneration-llama-2-13b-f", "provider": "sagemaker", "providerSlug": "sagemaker", "name": "meta-textgeneration-llama-2-13b-f", "displayName": "meta-textgeneration-llama-2-13b-f", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sagemaker/meta-textgeneration-llama-2-13b-f", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0 } }, { "id": "sagemaker/sagemaker/meta-textgeneration-llama-2-70b", "slug": "sagemaker-sagemaker-meta-textgeneration-llama-2-70b", "provider": "sagemaker", "providerSlug": "sagemaker", "name": "meta-textgeneration-llama-2-70b", "displayName": "meta-textgeneration-llama-2-70b", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sagemaker/meta-textgeneration-llama-2-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0 } }, { "id": "sagemaker/sagemaker/meta-textgeneration-llama-2-70b-b-f", "slug": "sagemaker-sagemaker-meta-textgeneration-llama-2-70b-b-f", "provider": "sagemaker", "providerSlug": "sagemaker", "name": "meta-textgeneration-llama-2-70b-b-f", "displayName": "meta-textgeneration-llama-2-70b-b-f", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sagemaker/meta-textgeneration-llama-2-70b-b-f", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0 } }, { "id": "sagemaker/sagemaker/meta-textgeneration-llama-2-7b", "slug": "sagemaker-sagemaker-meta-textgeneration-llama-2-7b", "provider": "sagemaker", "providerSlug": "sagemaker", "name": "meta-textgeneration-llama-2-7b", "displayName": "meta-textgeneration-llama-2-7b", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sagemaker/meta-textgeneration-llama-2-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0 } }, { "id": "sagemaker/sagemaker/meta-textgeneration-llama-2-7b-f", "slug": "sagemaker-sagemaker-meta-textgeneration-llama-2-7b-f", "provider": "sagemaker", "providerSlug": "sagemaker", "name": "meta-textgeneration-llama-2-7b-f", "displayName": "meta-textgeneration-llama-2-7b-f", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sagemaker/meta-textgeneration-llama-2-7b-f", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0 } }, { "id": "sambanova/sambanova/MiniMax-M2.7", "slug": "sambanova-sambanova-minimax-m2-7", "provider": "sambanova", "providerSlug": "sambanova", "name": "MiniMax-M2.7", "displayName": "MiniMax-M2.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 204800, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/MiniMax-M2.7", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "sambanova", "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "sambanova/sambanova/DeepSeek-R1", "slug": "sambanova-sambanova-deepseek-r1", "provider": "sambanova", "providerSlug": "sambanova", "name": "DeepSeek-R1", "displayName": "DeepSeek-R1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000007 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/DeepSeek-R1", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "sambanova", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000007, "source": "https://cloud.sambanova.ai/plans/pricing" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "sambanova/sambanova/DeepSeek-R1-Distill-Llama-70B", "slug": "sambanova-sambanova-deepseek-r1-distill-llama-70b", "provider": "sambanova", "providerSlug": "sambanova", "name": "DeepSeek-R1-Distill-Llama-70B", "displayName": "DeepSeek-R1-Distill-Llama-70B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7, "outputUsdPer1MTokens": 1.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000014 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/DeepSeek-R1-Distill-Llama-70B", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 7e-7, "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000014, "source": "https://cloud.sambanova.ai/plans/pricing" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "sambanova/sambanova/DeepSeek-V3-0324", "slug": "sambanova-sambanova-deepseek-v3-0324", "provider": "sambanova", "providerSlug": "sambanova", "name": "DeepSeek-V3-0324", "displayName": "DeepSeek-V3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.0000045 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/DeepSeek-V3-0324", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "sambanova", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000045, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "sambanova/sambanova/Llama-4-Maverick-17B-128E-Instruct", "slug": "sambanova-sambanova-llama-4-maverick-17b-128e-instruct", "provider": "sambanova", "providerSlug": "sambanova", "name": "Llama-4-Maverick-17B-128E-Instruct", "displayName": "Llama-4-Maverick-17B-128E-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.63, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.63, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.3e-7, "output_cost_per_token": 0.0000018 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/Llama-4-Maverick-17B-128E-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 6.3e-7, "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, "mode": "chat", "output_cost_per_token": 0.0000018, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "sambanova/sambanova/Llama-4-Scout-17B-16E-Instruct", "slug": "sambanova-sambanova-llama-4-scout-17b-16e-instruct", "provider": "sambanova", "providerSlug": "sambanova", "name": "Llama-4-Scout-17B-16E-Instruct", "displayName": "Llama-4-Scout-17B-16E-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 0.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 7e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/Llama-4-Scout-17B-16E-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "sambanova", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, "mode": "chat", "output_cost_per_token": 7e-7, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "sambanova/sambanova/Meta-Llama-3.1-405B-Instruct", "slug": "sambanova-sambanova-meta-llama-3-1-405b-instruct", "provider": "sambanova", "providerSlug": "sambanova", "name": "Meta-Llama-3.1-405B-Instruct", "displayName": "Meta-Llama-3.1-405B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/Meta-Llama-3.1-405B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "sambanova", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "sambanova/sambanova/Meta-Llama-3.1-8B-Instruct", "slug": "sambanova-sambanova-meta-llama-3-1-8b-instruct", "provider": "sambanova", "providerSlug": "sambanova", "name": "Meta-Llama-3.1-8B-Instruct", "displayName": "Meta-Llama-3.1-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/Meta-Llama-3.1-8B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "sambanova", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "sambanova/sambanova/Meta-Llama-3.2-1B-Instruct", "slug": "sambanova-sambanova-meta-llama-3-2-1b-instruct", "provider": "sambanova", "providerSlug": "sambanova", "name": "Meta-Llama-3.2-1B-Instruct", "displayName": "Meta-Llama-3.2-1B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/Meta-Llama-3.2-1B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 4e-8, "litellm_provider": "sambanova", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8e-8, "source": "https://cloud.sambanova.ai/plans/pricing" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "sambanova/sambanova/Meta-Llama-3.2-3B-Instruct", "slug": "sambanova-sambanova-meta-llama-3-2-3b-instruct", "provider": "sambanova", "providerSlug": "sambanova", "name": "Meta-Llama-3.2-3B-Instruct", "displayName": "Meta-Llama-3.2-3B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.16, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 1.6e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/Meta-Llama-3.2-3B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 8e-8, "litellm_provider": "sambanova", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.6e-7, "source": "https://cloud.sambanova.ai/plans/pricing" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "sambanova/sambanova/Meta-Llama-3.3-70B-Instruct", "slug": "sambanova-sambanova-meta-llama-3-3-70b-instruct", "provider": "sambanova", "providerSlug": "sambanova", "name": "Meta-Llama-3.3-70B-Instruct", "displayName": "Meta-Llama-3.3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/Meta-Llama-3.3-70B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "sambanova/sambanova/Meta-Llama-Guard-3-8B", "slug": "sambanova-sambanova-meta-llama-guard-3-8b", "provider": "sambanova", "providerSlug": "sambanova", "name": "Meta-Llama-Guard-3-8B", "displayName": "Meta-Llama-Guard-3-8B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/Meta-Llama-Guard-3-8B", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "sambanova", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://cloud.sambanova.ai/plans/pricing" } }, { "id": "sambanova/sambanova/QwQ-32B", "slug": "sambanova-sambanova-qwq-32b", "provider": "sambanova", "providerSlug": "sambanova", "name": "QwQ-32B", "displayName": "QwQ-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/QwQ-32B", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "sambanova", "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000001, "source": "https://cloud.sambanova.ai/plans/pricing" } }, { "id": "sambanova/sambanova/Qwen2-Audio-7B-Instruct", "slug": "sambanova-sambanova-qwen2-audio-7b-instruct", "provider": "sambanova", "providerSlug": "sambanova", "name": "Qwen2-Audio-7B-Instruct", "displayName": "Qwen2-Audio-7B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 100, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/Qwen2-Audio-7B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "sambanova", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0001, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_audio_input": true } }, { "id": "sambanova/sambanova/Qwen3-32B", "slug": "sambanova-sambanova-qwen3-32b", "provider": "sambanova", "providerSlug": "sambanova", "name": "Qwen3-32B", "displayName": "Qwen3-32B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/Qwen3-32B", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "sambanova", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-7, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true } }, { "id": "sambanova/sambanova/DeepSeek-V3.1", "slug": "sambanova-sambanova-deepseek-v3-1", "provider": "sambanova", "providerSlug": "sambanova", "name": "DeepSeek-V3.1", "displayName": "DeepSeek-V3.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.0000045 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/DeepSeek-V3.1", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.0000045, "litellm_provider": "sambanova", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "sambanova/sambanova/gpt-oss-120b", "slug": "sambanova-sambanova-gpt-oss-120b", "provider": "sambanova", "providerSlug": "sambanova", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.0000045 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sambanova/gpt-oss-120b", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.sambanova.ai/plans/pricing" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.0000045, "litellm_provider": "sambanova", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "snowflake/snowflake/claude-3-5-sonnet", "slug": "snowflake-snowflake-claude-3-5-sonnet", "provider": "snowflake", "providerSlug": "snowflake", "name": "claude-3-5-sonnet", "displayName": "claude-3-5-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 18000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "computer_use": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/claude-3-5-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 18000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "supports_computer_use": true }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "snowflake/snowflake/deepseek-r1", "slug": "snowflake-snowflake-deepseek-r1", "provider": "snowflake", "providerSlug": "snowflake", "name": "deepseek-r1", "displayName": "deepseek-r1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/deepseek-r1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "supports_reasoning": true }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "snowflake/snowflake/gemma-7b", "slug": "snowflake-snowflake-gemma-7b", "provider": "snowflake", "providerSlug": "snowflake", "name": "gemma-7b", "displayName": "gemma-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 8000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/gemma-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" }, "benchmarks": { "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "snowflake/snowflake/jamba-1.5-large", "slug": "snowflake-snowflake-jamba-1-5-large", "provider": "snowflake", "providerSlug": "snowflake", "name": "jamba-1.5-large", "displayName": "jamba-1.5-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 256000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/jamba-1.5-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/jamba-1.5-mini", "slug": "snowflake-snowflake-jamba-1-5-mini", "provider": "snowflake", "providerSlug": "snowflake", "name": "jamba-1.5-mini", "displayName": "jamba-1.5-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 256000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/jamba-1.5-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/jamba-instruct", "slug": "snowflake-snowflake-jamba-instruct", "provider": "snowflake", "providerSlug": "snowflake", "name": "jamba-instruct", "displayName": "jamba-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 256000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/jamba-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/llama2-70b-chat", "slug": "snowflake-snowflake-llama2-70b-chat", "provider": "snowflake", "providerSlug": "snowflake", "name": "llama2-70b-chat", "displayName": "llama2-70b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 4096, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/llama2-70b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/llama3-70b", "slug": "snowflake-snowflake-llama3-70b", "provider": "snowflake", "providerSlug": "snowflake", "name": "llama3-70b", "displayName": "llama3-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 8000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/llama3-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/llama3-8b", "slug": "snowflake-snowflake-llama3-8b", "provider": "snowflake", "providerSlug": "snowflake", "name": "llama3-8b", "displayName": "llama3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 8000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/llama3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/llama3.1-405b", "slug": "snowflake-snowflake-llama3-1-405b", "provider": "snowflake", "providerSlug": "snowflake", "name": "llama3.1-405b", "displayName": "llama3.1-405b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/llama3.1-405b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "snowflake/snowflake/llama3.1-70b", "slug": "snowflake-snowflake-llama3-1-70b", "provider": "snowflake", "providerSlug": "snowflake", "name": "llama3.1-70b", "displayName": "llama3.1-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/llama3.1-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "snowflake/snowflake/llama3.1-8b", "slug": "snowflake-snowflake-llama3-1-8b", "provider": "snowflake", "providerSlug": "snowflake", "name": "llama3.1-8b", "displayName": "llama3.1-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/llama3.1-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "snowflake/snowflake/llama3.2-1b", "slug": "snowflake-snowflake-llama3-2-1b", "provider": "snowflake", "providerSlug": "snowflake", "name": "llama3.2-1b", "displayName": "llama3.2-1b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/llama3.2-1b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "snowflake/snowflake/llama3.2-3b", "slug": "snowflake-snowflake-llama3-2-3b", "provider": "snowflake", "providerSlug": "snowflake", "name": "llama3.2-3b", "displayName": "llama3.2-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/llama3.2-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "snowflake/snowflake/llama3.3-70b", "slug": "snowflake-snowflake-llama3-3-70b", "provider": "snowflake", "providerSlug": "snowflake", "name": "llama3.3-70b", "displayName": "llama3.3-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/llama3.3-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "snowflake/snowflake/mistral-7b", "slug": "snowflake-snowflake-mistral-7b", "provider": "snowflake", "providerSlug": "snowflake", "name": "mistral-7b", "displayName": "mistral-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 32000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/mistral-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "snowflake/snowflake/mistral-large", "slug": "snowflake-snowflake-mistral-large", "provider": "snowflake", "providerSlug": "snowflake", "name": "mistral-large", "displayName": "mistral-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 32000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/mistral-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/mistral-large2", "slug": "snowflake-snowflake-mistral-large2", "provider": "snowflake", "providerSlug": "snowflake", "name": "mistral-large2", "displayName": "mistral-large2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/mistral-large2", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/mixtral-8x7b", "slug": "snowflake-snowflake-mixtral-8x7b", "provider": "snowflake", "providerSlug": "snowflake", "name": "mixtral-8x7b", "displayName": "mixtral-8x7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 32000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/mixtral-8x7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/reka-core", "slug": "snowflake-snowflake-reka-core", "provider": "snowflake", "providerSlug": "snowflake", "name": "reka-core", "displayName": "reka-core", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 32000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/reka-core", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/reka-flash", "slug": "snowflake-snowflake-reka-flash", "provider": "snowflake", "providerSlug": "snowflake", "name": "reka-flash", "displayName": "reka-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 100000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/reka-flash", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 100000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/snowflake-arctic", "slug": "snowflake-snowflake-snowflake-arctic", "provider": "snowflake", "providerSlug": "snowflake", "name": "snowflake-arctic", "displayName": "snowflake-arctic", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 4096, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/snowflake-arctic", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" } }, { "id": "snowflake/snowflake/snowflake-llama-3.1-405b", "slug": "snowflake-snowflake-snowflake-llama-3-1-405b", "provider": "snowflake", "providerSlug": "snowflake", "name": "snowflake-llama-3.1-405b", "displayName": "snowflake-llama-3.1-405b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 8000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/snowflake-llama-3.1-405b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "snowflake/snowflake/snowflake-llama-3.3-70b", "slug": "snowflake-snowflake-snowflake-llama-3-3-70b", "provider": "snowflake", "providerSlug": "snowflake", "name": "snowflake-llama-3.3-70b", "displayName": "snowflake-llama-3.3-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 8192, "maxInputTokens": 8000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "snowflake/snowflake-llama-3.3-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat" }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "stability/stability/sd3", "slug": "stability-stability-sd3", "provider": "stability", "providerSlug": "stability", "name": "sd3", "displayName": "sd3", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 65000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.065 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/sd3", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.065, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "stability/stability/sd3-large", "slug": "stability-stability-sd3-large", "provider": "stability", "providerSlug": "stability", "name": "sd3-large", "displayName": "sd3-large", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 65000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.065 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/sd3-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.065, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "stability/stability/sd3-large-turbo", "slug": "stability-stability-sd3-large-turbo", "provider": "stability", "providerSlug": "stability", "name": "sd3-large-turbo", "displayName": "sd3-large-turbo", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/sd3-large-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.04, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "stability/stability/sd3-medium", "slug": "stability-stability-sd3-medium", "provider": "stability", "providerSlug": "stability", "name": "sd3-medium", "displayName": "sd3-medium", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 35000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.035 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/sd3-medium", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.035, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "stability/stability/sd3.5-large", "slug": "stability-stability-sd3-5-large", "provider": "stability", "providerSlug": "stability", "name": "sd3.5-large", "displayName": "sd3.5-large", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 65000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.065 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/sd3.5-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.065, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "stability/stability/sd3.5-large-turbo", "slug": "stability-stability-sd3-5-large-turbo", "provider": "stability", "providerSlug": "stability", "name": "sd3.5-large-turbo", "displayName": "sd3.5-large-turbo", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/sd3.5-large-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.04, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "stability/stability/sd3.5-medium", "slug": "stability-stability-sd3-5-medium", "provider": "stability", "providerSlug": "stability", "name": "sd3.5-medium", "displayName": "sd3.5-medium", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 35000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.035 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/sd3.5-medium", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.035, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "stability/stability/stable-image-ultra", "slug": "stability-stability-stable-image-ultra", "provider": "stability", "providerSlug": "stability", "name": "stable-image-ultra", "displayName": "stable-image-ultra", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 80000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.08 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/stable-image-ultra", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.08, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "stability/stability/inpaint", "slug": "stability-stability-inpaint", "provider": "stability", "providerSlug": "stability", "name": "inpaint", "displayName": "inpaint", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 5000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/inpaint", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/outpaint", "slug": "stability-stability-outpaint", "provider": "stability", "providerSlug": "stability", "name": "outpaint", "displayName": "outpaint", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 4000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.004 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/outpaint", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.004, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/erase", "slug": "stability-stability-erase", "provider": "stability", "providerSlug": "stability", "name": "erase", "displayName": "erase", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 5000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/erase", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/search-and-replace", "slug": "stability-stability-search-and-replace", "provider": "stability", "providerSlug": "stability", "name": "search-and-replace", "displayName": "search-and-replace", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 5000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/search-and-replace", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/search-and-recolor", "slug": "stability-stability-search-and-recolor", "provider": "stability", "providerSlug": "stability", "name": "search-and-recolor", "displayName": "search-and-recolor", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 5000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/search-and-recolor", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/remove-background", "slug": "stability-stability-remove-background", "provider": "stability", "providerSlug": "stability", "name": "remove-background", "displayName": "remove-background", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 5000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/remove-background", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/replace-background-and-relight", "slug": "stability-stability-replace-background-and-relight", "provider": "stability", "providerSlug": "stability", "name": "replace-background-and-relight", "displayName": "replace-background-and-relight", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 8000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.008 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/replace-background-and-relight", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.008, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/sketch", "slug": "stability-stability-sketch", "provider": "stability", "providerSlug": "stability", "name": "sketch", "displayName": "sketch", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 5000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/sketch", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/structure", "slug": "stability-stability-structure", "provider": "stability", "providerSlug": "stability", "name": "structure", "displayName": "structure", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 5000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/structure", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/style", "slug": "stability-stability-style", "provider": "stability", "providerSlug": "stability", "name": "style", "displayName": "style", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 5000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/style", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/style-transfer", "slug": "stability-stability-style-transfer", "provider": "stability", "providerSlug": "stability", "name": "style-transfer", "displayName": "style-transfer", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 8000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.008 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/style-transfer", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.008, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/fast", "slug": "stability-stability-fast", "provider": "stability", "providerSlug": "stability", "name": "fast", "displayName": "fast", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 2000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.002 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/fast", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.002, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/conservative", "slug": "stability-stability-conservative", "provider": "stability", "providerSlug": "stability", "name": "conservative", "displayName": "conservative", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/conservative", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.04, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/creative", "slug": "stability-stability-creative", "provider": "stability", "providerSlug": "stability", "name": "creative", "displayName": "creative", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/creative", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.06, "supported_endpoints": [ "/v1/images/edits" ] } }, { "id": "stability/stability/stable-image-core", "slug": "stability-stability-stable-image-core", "provider": "stability", "providerSlug": "stability", "name": "stable-image-core", "displayName": "stable-image-core", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 30000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.03 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability/stable-image-core", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.03, "supported_endpoints": [ "/v1/images/generations" ] } }, { "id": "bedrock/stability.sd3-5-large-v1:0", "slug": "bedrock-stability-sd3-5-large-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.sd3-5-large-v1:0", "displayName": "stability.sd3-5-large-v1:0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 80000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.08 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.sd3-5-large-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 } }, { "id": "bedrock/stability.sd3-large-v1:0", "slug": "bedrock-stability-sd3-large-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.sd3-large-v1:0", "displayName": "stability.sd3-large-v1:0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 80000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.08 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.sd3-large-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 } }, { "id": "bedrock/stability.stable-image-core-v1:0", "slug": "bedrock-stability-stable-image-core-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-core-v1:0", "displayName": "stability.stable-image-core-v1:0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-core-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 } }, { "id": "bedrock/stability.stable-conservative-upscale-v1:0", "slug": "bedrock-stability-stable-conservative-upscale-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-conservative-upscale-v1:0", "displayName": "stability.stable-conservative-upscale-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 400000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.4 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-conservative-upscale-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.4 } }, { "id": "bedrock/stability.stable-creative-upscale-v1:0", "slug": "bedrock-stability-stable-creative-upscale-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-creative-upscale-v1:0", "displayName": "stability.stable-creative-upscale-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 600000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.6 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-creative-upscale-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.6 } }, { "id": "bedrock/stability.stable-fast-upscale-v1:0", "slug": "bedrock-stability-stable-fast-upscale-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-fast-upscale-v1:0", "displayName": "stability.stable-fast-upscale-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 30000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.03 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-fast-upscale-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.03 } }, { "id": "bedrock/stability.stable-outpaint-v1:0", "slug": "bedrock-stability-stable-outpaint-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-outpaint-v1:0", "displayName": "stability.stable-outpaint-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-outpaint-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.06 } }, { "id": "bedrock/stability.stable-image-control-sketch-v1:0", "slug": "bedrock-stability-stable-image-control-sketch-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-control-sketch-v1:0", "displayName": "stability.stable-image-control-sketch-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 70000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.07 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-control-sketch-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 } }, { "id": "bedrock/stability.stable-image-control-structure-v1:0", "slug": "bedrock-stability-stable-image-control-structure-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-control-structure-v1:0", "displayName": "stability.stable-image-control-structure-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 70000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.07 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-control-structure-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 } }, { "id": "bedrock/stability.stable-image-erase-object-v1:0", "slug": "bedrock-stability-stable-image-erase-object-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-erase-object-v1:0", "displayName": "stability.stable-image-erase-object-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 70000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.07 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-erase-object-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 } }, { "id": "bedrock/stability.stable-image-inpaint-v1:0", "slug": "bedrock-stability-stable-image-inpaint-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-inpaint-v1:0", "displayName": "stability.stable-image-inpaint-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 70000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.07 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-inpaint-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 } }, { "id": "bedrock/stability.stable-image-remove-background-v1:0", "slug": "bedrock-stability-stable-image-remove-background-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-remove-background-v1:0", "displayName": "stability.stable-image-remove-background-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 70000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.07 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-remove-background-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 } }, { "id": "bedrock/stability.stable-image-search-recolor-v1:0", "slug": "bedrock-stability-stable-image-search-recolor-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-search-recolor-v1:0", "displayName": "stability.stable-image-search-recolor-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 70000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.07 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-search-recolor-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 } }, { "id": "bedrock/stability.stable-image-search-replace-v1:0", "slug": "bedrock-stability-stable-image-search-replace-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-search-replace-v1:0", "displayName": "stability.stable-image-search-replace-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 70000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.07 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-search-replace-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 } }, { "id": "bedrock/stability.stable-image-style-guide-v1:0", "slug": "bedrock-stability-stable-image-style-guide-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-style-guide-v1:0", "displayName": "stability.stable-image-style-guide-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 70000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.07 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-style-guide-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 } }, { "id": "bedrock/stability.stable-style-transfer-v1:0", "slug": "bedrock-stability-stable-style-transfer-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-style-transfer-v1:0", "displayName": "stability.stable-style-transfer-v1:0", "mode": "image_edit", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 80000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.08 } }, "limits": { "contextWindow": null, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-style-transfer-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.08 } }, { "id": "bedrock/stability.stable-image-core-v1:1", "slug": "bedrock-stability-stable-image-core-v1-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-core-v1:1", "displayName": "stability.stable-image-core-v1:1", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-core-v1:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 } }, { "id": "bedrock/stability.stable-image-ultra-v1:0", "slug": "bedrock-stability-stable-image-ultra-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-ultra-v1:0", "displayName": "stability.stable-image-ultra-v1:0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 140000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.14 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-ultra-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 } }, { "id": "bedrock/stability.stable-image-ultra-v1:1", "slug": "bedrock-stability-stable-image-ultra-v1-1", "provider": "Bedrock", "providerSlug": "bedrock", "name": "stability.stable-image-ultra-v1:1", "displayName": "stability.stable-image-ultra-v1:1", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 140000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.14 } }, "limits": { "contextWindow": 77, "maxInputTokens": 77, "maxOutputTokens": null, "maxTokens": 77, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "stability.stable-image-ultra-v1:1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 } }, { "id": "openai/standard/1024-x-1024/dall-e-3", "slug": "openai-standard-1024-x-1024-dall-e-3", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-3", "displayName": "dall-e-3 (1024x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 3.81469e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 3.81469e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "standard/1024-x-1024/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 3.81469e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0 } }, { "id": "openai/standard/1024-x-1792/dall-e-3", "slug": "openai-standard-1024-x-1792-dall-e-3", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-3", "displayName": "dall-e-3 (1024x1792)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 4.359e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 4.359e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "standard/1024-x-1792/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 4.359e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0 } }, { "id": "openai/standard/1792-x-1024/dall-e-3", "slug": "openai-standard-1792-x-1024-dall-e-3", "provider": "OpenAI", "providerSlug": "openai", "name": "dall-e-3", "displayName": "dall-e-3 (1792x1024)", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": 4.359e-8, "perPixelOutputUsd": 0, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_pixel": 4.359e-8, "output_cost_per_pixel": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "standard/1792-x-1024/dall-e-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_pixel": 4.359e-8, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0 } }, { "id": "linkup/linkup/search", "slug": "linkup-linkup-search", "provider": "linkup", "providerSlug": "linkup", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 5.87, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.00587 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "linkup/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.00587, "litellm_provider": "linkup", "mode": "search", "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "linkup/linkup/search-deep", "slug": "linkup-linkup-search-deep", "provider": "linkup", "providerSlug": "linkup", "name": "search-deep", "displayName": "search-deep", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 58.67, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.05867 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "linkup/search-deep", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.05867, "litellm_provider": "linkup", "mode": "search", "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "tavily/tavily/search", "slug": "tavily-tavily-search", "provider": "tavily", "providerSlug": "tavily", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 8, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.008 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "tavily/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.008, "litellm_provider": "tavily", "mode": "search", "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "tavily/tavily/search-advanced", "slug": "tavily-tavily-search-advanced", "provider": "tavily", "providerSlug": "tavily", "name": "search-advanced", "displayName": "search-advanced", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 16, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.016 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "tavily/search-advanced", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.016, "litellm_provider": "tavily", "mode": "search", "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "text-completion-codestral/text-completion-codestral/codestral-2405", "slug": "text-completion-codestral-text-completion-codestral-codestral-2405", "provider": "text-completion-codestral", "providerSlug": "text-completion-codestral", "name": "codestral-2405", "displayName": "codestral-2405", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-completion-codestral/codestral-2405", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.mistral.ai/capabilities/code_generation/" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "completion", "output_cost_per_token": 0, "source": "https://docs.mistral.ai/capabilities/code_generation/" }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "text-completion-codestral/text-completion-codestral/codestral-latest", "slug": "text-completion-codestral-text-completion-codestral-codestral-latest", "provider": "text-completion-codestral", "providerSlug": "text-completion-codestral", "name": "codestral-latest", "displayName": "codestral-latest", "mode": "completion", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-completion-codestral/codestral-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.mistral.ai/capabilities/code_generation/" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "completion", "output_cost_per_token": 0, "source": "https://docs.mistral.ai/capabilities/code_generation/" }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "vertex_ai-embedding-models/text-embedding-004", "slug": "vertex_ai-embedding-models-text-embedding-004", "provider": "vertex_ai-embedding-models", "providerSlug": "vertex_ai-embedding-models", "name": "text-embedding-004", "displayName": "text-embedding-004", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 2.5e-8, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 2.5e-8, "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": null, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 768, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-01-14" }, "source": { "type": "litellm", "litellmKey": "text-embedding-004", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "rawLitellm": { "deprecation_date": "2026-01-14", "input_cost_per_character": 2.5e-8, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" } }, { "id": "vertex_ai-embedding-models/text-embedding-005", "slug": "vertex_ai-embedding-models-text-embedding-005", "provider": "vertex_ai-embedding-models", "providerSlug": "vertex_ai-embedding-models", "name": "text-embedding-005", "displayName": "text-embedding-005", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 2.5e-8, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 2.5e-8, "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": null, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 768, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-embedding-005", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "rawLitellm": { "input_cost_per_character": 2.5e-8, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" } }, { "id": "openai/text-embedding-3-large", "slug": "openai-text-embedding-3-large", "provider": "OpenAI", "providerSlug": "openai", "name": "text-embedding-3-large", "displayName": "text-embedding-3-large", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.065, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "input_cost_per_token_batches": 6.5e-8, "output_cost_per_token": 0, "output_cost_per_token_batches": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-embedding-3-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.3e-7, "input_cost_per_token_batches": 6.5e-8, "litellm_provider": "openai", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0, "output_cost_per_token_batches": 0, "output_vector_size": 3072 } }, { "id": "openai/text-embedding-3-small", "slug": "openai-text-embedding-3-small", "provider": "OpenAI", "providerSlug": "openai", "name": "text-embedding-3-small", "displayName": "text-embedding-3-small", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.01, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "input_cost_per_token_batches": 1e-8, "output_cost_per_token": 0, "output_cost_per_token_batches": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1536, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-embedding-3-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-8, "input_cost_per_token_batches": 1e-8, "litellm_provider": "openai", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0, "output_cost_per_token_batches": 0, "output_vector_size": 1536 } }, { "id": "openai/text-embedding-ada-002", "slug": "openai-text-embedding-ada-002", "provider": "OpenAI", "providerSlug": "openai", "name": "text-embedding-ada-002", "displayName": "text-embedding-ada-002", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 1536, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-embedding-ada-002", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "openai", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 1536 } }, { "id": "openai/text-embedding-ada-002-v2", "slug": "openai-text-embedding-ada-002-v2", "provider": "OpenAI", "providerSlug": "openai", "name": "text-embedding-ada-002-v2", "displayName": "text-embedding-ada-002-v2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.049999999999999996, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "input_cost_per_token_batches": 5e-8, "output_cost_per_token": 0, "output_cost_per_token_batches": 0 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 8191, "maxOutputTokens": null, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-embedding-ada-002-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "input_cost_per_token_batches": 5e-8, "litellm_provider": "openai", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0, "output_cost_per_token_batches": 0 } }, { "id": "vertex_ai-embedding-models/text-embedding-large-exp-03-07", "slug": "vertex_ai-embedding-models-text-embedding-large-exp-03-07", "provider": "vertex_ai-embedding-models", "providerSlug": "vertex_ai-embedding-models", "name": "text-embedding-large-exp-03-07", "displayName": "text-embedding-large-exp-03-07", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 2.5e-8, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 2.5e-8, "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 3072, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-embedding-large-exp-03-07", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "rawLitellm": { "input_cost_per_character": 2.5e-8, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" } }, { "id": "vertex_ai-embedding-models/text-embedding-preview-0409", "slug": "vertex_ai-embedding-models-text-embedding-preview-0409", "provider": "vertex_ai-embedding-models", "providerSlug": "vertex_ai-embedding-models", "name": "text-embedding-preview-0409", "displayName": "text-embedding-preview-0409", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.0062499999999999995, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.0062499999999999995, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.005, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.25e-9, "input_cost_per_token_batch_requests": 5e-9, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 3072, "maxInputTokens": 3072, "maxOutputTokens": null, "maxTokens": 3072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 768, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-embedding-preview-0409", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "input_cost_per_token": 6.25e-9, "input_cost_per_token_batch_requests": 5e-9, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 3072, "max_tokens": 3072, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "id": "openai/text-moderation-007", "slug": "openai-text-moderation-007", "provider": "OpenAI", "providerSlug": "openai", "name": "text-moderation-007", "displayName": "text-moderation-007", "mode": "moderation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 32768, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-moderation-007", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0 } }, { "id": "openai/text-moderation-latest", "slug": "openai-text-moderation-latest", "provider": "OpenAI", "providerSlug": "openai", "name": "text-moderation-latest", "displayName": "text-moderation-latest", "mode": "moderation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 32768, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-moderation-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0 } }, { "id": "openai/text-moderation-stable", "slug": "openai-text-moderation-stable", "provider": "OpenAI", "providerSlug": "openai", "name": "text-moderation-stable", "displayName": "text-moderation-stable", "mode": "moderation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 32768, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-moderation-stable", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0 } }, { "id": "vertex_ai-embedding-models/text-multilingual-embedding-002", "slug": "vertex_ai-embedding-models-text-multilingual-embedding-002", "provider": "vertex_ai-embedding-models", "providerSlug": "vertex_ai-embedding-models", "name": "text-multilingual-embedding-002", "displayName": "text-multilingual-embedding-002", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 2.5e-8, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 2.5e-8, "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": null, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 768, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-multilingual-embedding-002", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "rawLitellm": { "input_cost_per_character": 2.5e-8, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" } }, { "id": "vertex_ai-text-models/text-unicorn", "slug": "vertex_ai-text-models-text-unicorn", "provider": "vertex_ai-text-models", "providerSlug": "vertex_ai-text-models", "name": "text-unicorn", "displayName": "text-unicorn", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.000028 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 8192, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-unicorn", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 0.000028, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } }, { "id": "vertex_ai-text-models/text-unicorn@001", "slug": "vertex_ai-text-models-text-unicorn-001", "provider": "vertex_ai-text-models", "providerSlug": "vertex_ai-text-models", "name": "text-unicorn@001", "displayName": "text-unicorn@001", "mode": "completion", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.000028 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 8192, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "text-unicorn@001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 0.000028, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" } }, { "id": "together_ai/together-ai-21.1b-41b", "slug": "together_ai-together-ai-21-1b-41b", "provider": "Together AI", "providerSlug": "together_ai", "name": "together-ai-21.1b-41b", "displayName": "together-ai-21.1b-41b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together-ai-21.1b-41b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8e-7 } }, { "id": "together_ai/together-ai-4.1b-8b", "slug": "together_ai-together-ai-4-1b-8b", "provider": "Together AI", "providerSlug": "together_ai", "name": "together-ai-4.1b-8b", "displayName": "together-ai-4.1b-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together-ai-4.1b-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 2e-7 } }, { "id": "together_ai/together-ai-41.1b-80b", "slug": "together_ai-together-ai-41-1b-80b", "provider": "Together AI", "providerSlug": "together_ai", "name": "together-ai-41.1b-80b", "displayName": "together-ai-41.1b-80b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together-ai-41.1b-80b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 9e-7 } }, { "id": "together_ai/together-ai-8.1b-21b", "slug": "together_ai-together-ai-8-1b-21b", "provider": "Together AI", "providerSlug": "together_ai", "name": "together-ai-8.1b-21b", "displayName": "together-ai-8.1b-21b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 1000, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": 1000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together-ai-8.1b-21b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "together_ai", "max_tokens": 1000, "mode": "chat", "output_cost_per_token": 3e-7 } }, { "id": "together_ai/together-ai-81.1b-110b", "slug": "together_ai-together-ai-81-1b-110b", "provider": "Together AI", "providerSlug": "together_ai", "name": "together-ai-81.1b-110b", "displayName": "together-ai-81.1b-110b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.7999999999999998, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.7999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.0000018 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together-ai-81.1b-110b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000018, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 0.0000018 } }, { "id": "together_ai/together-ai-embedding-151m-to-350m", "slug": "together_ai-together-ai-embedding-151m-to-350m", "provider": "Together AI", "providerSlug": "together_ai", "name": "together-ai-embedding-151m-to-350m", "displayName": "together-ai-embedding-151m-to-350m", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.016, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.016, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.6e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together-ai-embedding-151m-to-350m", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.6e-8, "litellm_provider": "together_ai", "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "together_ai/together-ai-embedding-up-to-150m", "slug": "together_ai-together-ai-embedding-up-to-150m", "provider": "Together AI", "providerSlug": "together_ai", "name": "together-ai-embedding-up-to-150m", "displayName": "together-ai-embedding-up-to-150m", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.008, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.008, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-9, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together-ai-embedding-up-to-150m", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-9, "litellm_provider": "together_ai", "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "together_ai/together_ai/baai/bge-base-en-v1.5", "slug": "together_ai-together_ai-baai-bge-base-en-v1-5", "provider": "Together AI", "providerSlug": "together_ai", "name": "bge-base-en-v1.5", "displayName": "bge-base-en-v1.5", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.008, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.008, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-9, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 768, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/baai/bge-base-en-v1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-9, "litellm_provider": "together_ai", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768 }, "benchmarks": { "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "together_ai/together_ai/BAAI/bge-base-en-v1.5", "slug": "together_ai-together_ai-baai-bge-base-en-v1-5-2", "provider": "Together AI", "providerSlug": "together_ai", "name": "bge-base-en-v1.5", "displayName": "bge-base-en-v1.5", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.008, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.008, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-9, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": 512, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": 768, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/BAAI/bge-base-en-v1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-9, "litellm_provider": "together_ai", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768 }, "benchmarks": { "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "together_ai/together-ai-up-to-4b", "slug": "together_ai-together-ai-up-to-4b", "provider": "Together AI", "providerSlug": "together_ai", "name": "together-ai-up-to-4b", "displayName": "together-ai-up-to-4b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together-ai-up-to-4b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1e-7 } }, { "id": "together_ai/together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo", "slug": "together_ai-together_ai-qwen-qwen2-5-72b-instruct-turbo", "provider": "Together AI", "providerSlug": "together_ai", "name": "Qwen2.5-72B-Instruct-Turbo", "displayName": "Qwen2.5-72B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-06", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/inference-models" ], "manual_model_modalities_note": "Together AI exact route id from official chat model catalog.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." } } }, { "id": "together_ai/together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo", "slug": "together_ai-together_ai-qwen-qwen2-5-7b-instruct-turbo", "provider": "Together AI", "providerSlug": "together_ai", "name": "Qwen2.5-7B-Instruct-Turbo", "displayName": "Qwen2.5-7B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/inference-models" ], "manual_model_modalities_note": "Together AI exact route id from official chat model catalog." }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." } } }, { "id": "together_ai/together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "slug": "together_ai-together_ai-qwen-qwen3-235b-a22b-instruct-2507-tput", "provider": "Together AI", "providerSlug": "together_ai", "name": "Qwen3-235B-A22B-Instruct-2507-tput", "displayName": "Qwen3-235B-A22B-Instruct-2507-tput", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": null, "maxInputTokens": 262000, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "together_ai", "max_input_tokens": 262000, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/inference-models" ], "manual_model_modalities_note": "Together AI exact route id from official chat model catalog." } }, { "id": "together_ai/together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507", "slug": "together_ai-together_ai-qwen-qwen3-235b-a22b-thinking-2507", "provider": "Together AI", "providerSlug": "together_ai", "name": "Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen3-235B-A22B-Thinking-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.65, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.65, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": null, "maxInputTokens": 256000, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-04-16", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507" }, "rawLitellm": { "input_cost_per_token": 6.5e-7, "litellm_provider": "together_ai", "max_input_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/inference-models" ], "manual_model_modalities_note": "Together AI exact route id from official chat model catalog.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." } }, { "id": "together_ai/together_ai/Qwen/Qwen3-235B-A22B-fp8-tput", "slug": "together_ai-together_ai-qwen-qwen3-235b-a22b-fp8-tput", "provider": "Together AI", "providerSlug": "together_ai", "name": "Qwen3-235B-A22B-fp8-tput", "displayName": "Qwen3-235B-A22B-fp8-tput", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": 40000, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-06", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "together_ai", "max_input_tokens": 40000, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/inference-models" ], "manual_model_modalities_note": "Together AI exact route id from official chat model catalog.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." } }, { "id": "together_ai/together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "slug": "together_ai-together_ai-qwen-qwen3-coder-480b-a35b-instruct-fp8", "provider": "Together AI", "providerSlug": "together_ai", "name": "Qwen3-Coder-480B-A35B-Instruct-FP8", "displayName": "Qwen3-Coder-480B-A35B-Instruct-FP8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": null, "maxInputTokens": 256000, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "deprecated", "announcementDate": null, "shutdownDate": "2026-06-04", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this future serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "together_ai", "max_input_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/inference-models" ], "manual_model_modalities_note": "Together AI exact route id from official chat model catalog.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this future serverless removal date." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "together_ai/together_ai/deepseek-ai/DeepSeek-R1", "slug": "together_ai-together_ai-deepseek-ai-deepseek-r1", "provider": "Together AI", "providerSlug": "together_ai", "name": "DeepSeek-R1", "displayName": "DeepSeek-R1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000007 } }, "limits": { "contextWindow": 20480, "maxInputTokens": 128000, "maxOutputTokens": 20480, "maxTokens": 20480, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/deepseek-ai/DeepSeek-R1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "together_ai", "max_input_tokens": 128000, "max_output_tokens": 20480, "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 0.000007, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/inference/chat/reasoning", "https://docs.together.ai/docs/function-calling", "https://docs.together.ai/docs/changelog" ], "manual_model_modalities_note": "Together AI exact route id from official reasoning docs.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "together_ai/together_ai/deepseek-ai/DeepSeek-R1-0528-tput", "slug": "together_ai-together_ai-deepseek-ai-deepseek-r1-0528-tput", "provider": "Together AI", "providerSlug": "together_ai", "name": "DeepSeek-R1-0528-tput", "displayName": "DeepSeek-R1-0528-tput", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.55, "outputUsdPer1MTokens": 2.1900000000000004, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.55, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219 } }, "limits": { "contextWindow": null, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-03", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/deepseek-ai/DeepSeek-R1-0528-tput", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/deepseek-r1-0528-throughput" }, "rawLitellm": { "input_cost_per_token": 5.5e-7, "litellm_provider": "together_ai", "max_input_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000219, "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models", "https://docs.together.ai/docs/changelog", "https://docs.together.ai/docs/deprecations" ], "manual_model_modalities_note": "Together AI exact route id from official serverless catalog.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "together_ai/together_ai/deepseek-ai/DeepSeek-V3", "slug": "together_ai-together_ai-deepseek-ai-deepseek-v3", "provider": "Together AI", "providerSlug": "together_ai", "name": "DeepSeek-V3", "displayName": "DeepSeek-V3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000125 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65536, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/deepseek-ai/DeepSeek-V3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000125, "litellm_provider": "together_ai", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models", "https://docs.together.ai/docs/fine-tuning-models", "https://docs.together.ai/docs/function-calling" ], "manual_model_modalities_note": "Together AI exact route id from official chat and support docs." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "together_ai/together_ai/deepseek-ai/DeepSeek-V3.1", "slug": "together_ai-together_ai-deepseek-ai-deepseek-v3-1", "provider": "Together AI", "providerSlug": "together_ai", "name": "DeepSeek-V3.1", "displayName": "DeepSeek-V3.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000017 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/deepseek-ai/DeepSeek-V3.1", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/deepseek-v3-1" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "together_ai", "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000017, "source": "https://www.together.ai/models/deepseek-v3-1", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "max_input_tokens": 128000, "max_output_tokens": 16384, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models", "https://docs.together.ai/docs/inference/chat/reasoning", "https://docs.together.ai/docs/deepseek-3-1-quickstart" ], "manual_model_modalities_note": "Together AI exact route id from official serverless catalog.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "together_ai/together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo", "slug": "together_ai-together_ai-meta-llama-llama-3-2-3b-instruct-turbo", "provider": "Together AI", "providerSlug": "together_ai", "name": "Llama-3.2-3B-Instruct-Turbo", "displayName": "Llama-3.2-3B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-03-06", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models" ], "manual_model_modalities_note": "Together AI exact route id from official serverless catalog.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "together_ai/together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo", "slug": "together_ai-together_ai-meta-llama-llama-3-3-70b-instruct-turbo", "provider": "Together AI", "providerSlug": "together_ai", "name": "Llama-3.3-70B-Instruct-Turbo", "displayName": "Llama-3.3-70B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.88, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.88, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8.8e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8.8e-7, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8.8e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models", "https://docs.together.ai/docs/function-calling" ], "manual_model_modalities_note": "Together AI exact route id from official serverless catalog." }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "together_ai/together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free", "slug": "together_ai-together_ai-meta-llama-llama-3-3-70b-instruct-turbo-free", "provider": "Together AI", "providerSlug": "together_ai", "name": "Llama-3.3-70B-Instruct-Turbo-Free", "displayName": "Llama-3.3-70B-Instruct-Turbo-Free", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/deprecations", "https://docs.together.ai/docs/serverless/models" ], "manual_model_modalities_note": "Together AI exact deprecated route id from official docs." }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "together_ai/together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "slug": "together_ai-together_ai-meta-llama-llama-4-maverick-17b-128e-instruct-fp8", "provider": "Together AI", "providerSlug": "together_ai", "name": "Llama-4-Maverick-17B-128E-Instruct-FP8", "displayName": "Llama-4-Maverick-17B-128E-Instruct-FP8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 0.85, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 8.5e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-03-31", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.7e-7, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8.5e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/llama4-quickstart" ], "manual_model_modalities_note": "Together AI exact route id from official Llama 4 quickstart.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "together_ai/together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct", "slug": "together_ai-together_ai-meta-llama-llama-4-scout-17b-16e-instruct", "provider": "Together AI", "providerSlug": "together_ai", "name": "Llama-4-Scout-17B-16E-Instruct", "displayName": "Llama-4-Scout-17B-16E-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": 0.59, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 5.9e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-06", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.8e-7, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 5.9e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/llama4-quickstart" ], "manual_model_modalities_note": "Together AI exact route id from official Llama 4 quickstart.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "together_ai/together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "slug": "together_ai-together_ai-meta-llama-meta-llama-3-1-405b-instruct-turbo", "provider": "Together AI", "providerSlug": "together_ai", "name": "Meta-Llama-3.1-405B-Instruct-Turbo", "displayName": "Meta-Llama-3.1-405B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.5, "outputUsdPer1MTokens": 3.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000035, "output_cost_per_token": 0.0000035 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-06", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000035, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 0.0000035, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/reference", "https://docs.together.ai/docs/deprecations" ], "manual_model_modalities_note": "Together AI exact route id from official chat docs.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "together_ai/together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "slug": "together_ai-together_ai-meta-llama-meta-llama-3-1-70b-instruct-turbo", "provider": "Together AI", "providerSlug": "together_ai", "name": "Meta-Llama-3.1-70B-Instruct-Turbo", "displayName": "Meta-Llama-3.1-70B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.88, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.88, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8.8e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-25", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8.8e-7, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8.8e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/reference", "https://docs.together.ai/docs/serverless/models" ], "manual_model_modalities_note": "Together AI exact route id from official chat docs.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "together_ai/together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "slug": "together_ai-together_ai-meta-llama-meta-llama-3-1-8b-instruct-turbo", "provider": "Together AI", "providerSlug": "together_ai", "name": "Meta-Llama-3.1-8B-Instruct-Turbo", "displayName": "Meta-Llama-3.1-8B-Instruct-Turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": 0.18, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 1.8e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-03-06", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.8e-7, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.8e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/reference", "https://docs.together.ai/docs/serverless/models" ], "manual_model_modalities_note": "Together AI exact route id from official chat docs.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "together_ai/together_ai/mistralai/Mistral-7B-Instruct-v0.1", "slug": "together_ai-together_ai-mistralai-mistral-7b-instruct-v0-1", "provider": "Together AI", "providerSlug": "together_ai", "name": "Mistral-7B-Instruct-v0.1", "displayName": "Mistral-7B-Instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/mistralai/Mistral-7B-Instruct-v0.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/fine-tuning-byom", "https://docs.together.ai/reference/completions-1" ], "manual_model_modalities_note": "Together AI exact route id from official docs." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "together_ai/together_ai/mistralai/Mistral-Small-24B-Instruct-2501", "slug": "together_ai-together_ai-mistralai-mistral-small-24b-instruct-2501", "provider": "Together AI", "providerSlug": "together_ai", "name": "Mistral-Small-24B-Instruct-2501", "displayName": "Mistral-Small-24B-Instruct-2501", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-04-02", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/mistralai/Mistral-Small-24B-Instruct-2501", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/inference-models", "https://docs.mistral.ai/models/model-cards/mistral-small-3-0-25-01" ], "manual_model_modalities_note": "Together AI exact route id from official docs.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." } }, { "id": "together_ai/together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1", "slug": "together_ai-together_ai-mistralai-mixtral-8x7b-instruct-v0-1", "provider": "Together AI", "providerSlug": "together_ai", "name": "Mixtral-8x7B-Instruct-v0.1", "displayName": "Mixtral-8x7B-Instruct-v0.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-04-16", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models", "https://docs.together.ai/docs/fine-tuning-models", "https://docs.together.ai/docs/fine-tuning-byom", "https://docs.together.ai/reference/completions-1" ], "manual_model_modalities_note": "Together AI exact route id from official docs.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." } }, { "id": "together_ai/together_ai/moonshotai/Kimi-K2-Instruct", "slug": "together_ai-together_ai-moonshotai-kimi-k2-instruct", "provider": "Together AI", "providerSlug": "together_ai", "name": "Kimi-K2-Instruct", "displayName": "Kimi-K2-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/moonshotai/Kimi-K2-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/kimi-k2-instruct" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://www.together.ai/models/kimi-k2-instruct", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models", "https://docs.together.ai/docs/kimi-k2-quickstart" ], "manual_model_modalities_note": "Together AI exact route id from official serverless catalog." } }, { "id": "together_ai/together_ai/openai/gpt-oss-120b", "slug": "together_ai-together_ai-openai-gpt-oss-120b", "provider": "Together AI", "providerSlug": "together_ai", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/openai/gpt-oss-120b", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/gpt-oss-120b" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://www.together.ai/models/gpt-oss-120b", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models", "https://docs.together.ai/docs/inference/chat/reasoning" ], "manual_model_modalities_note": "Together AI exact route id from official reasoning docs." }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "together_ai/together_ai/openai/gpt-oss-20b", "slug": "together_ai-together_ai-openai-gpt-oss-20b", "provider": "Together AI", "providerSlug": "together_ai", "name": "gpt-oss-20b", "displayName": "gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/openai/gpt-oss-20b", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/gpt-oss-20b" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "together_ai", "max_input_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-7, "source": "https://www.together.ai/models/gpt-oss-20b", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models", "https://docs.together.ai/docs/gpt-oss" ], "manual_model_modalities_note": "Together AI exact route id from official docs." }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "together_ai/together_ai/togethercomputer/CodeLlama-34b-Instruct", "slug": "together_ai-together_ai-togethercomputer-codellama-34b-instruct", "provider": "Together AI", "providerSlug": "together_ai", "name": "CodeLlama-34b-Instruct", "displayName": "CodeLlama-34b-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/togethercomputer/CodeLlama-34b-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://together-ai-preview.mintlify.app/inference-chat/json-mode", "https://github.com/meta-llama/codellama/blob/main/MODEL_CARD.md" ], "manual_model_modalities_note": "Together AI exact route id from official docs." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "together_ai/together_ai/zai-org/GLM-4.5-Air-FP8", "slug": "together_ai-together_ai-zai-org-glm-4-5-air-fp8", "provider": "Together AI", "providerSlug": "together_ai", "name": "GLM-4.5-Air-FP8", "displayName": "GLM-4.5-Air-FP8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000011 } }, "limits": { "contextWindow": null, "maxInputTokens": 128000, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-04-02", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/zai-org/GLM-4.5-Air-FP8", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/glm-4-5-air" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "together_ai", "max_input_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000011, "source": "https://www.together.ai/models/glm-4-5-air", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models", "https://docs.together.ai/docs/changelog" ], "manual_model_modalities_note": "Together AI exact route id from official docs.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "together_ai/together_ai/zai-org/GLM-4.6", "slug": "together_ai-together_ai-zai-org-glm-4-6", "provider": "Together AI", "providerSlug": "together_ai", "name": "GLM-4.6", "displayName": "GLM-4.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 200000, "maxInputTokens": 200000, "maxOutputTokens": 200000, "maxTokens": 200000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/zai-org/GLM-4.6", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/glm-4-6" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "together_ai", "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 0.0000022, "source": "https://www.together.ai/models/glm-4-6", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/serverless/models", "https://docs.together.ai/docs/changelog" ], "manual_model_modalities_note": "Together AI exact route id from official docs." }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_zaiglm46_benchmarkleaderboard_282": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_zaiglm46_benchmarkleaderboard_283": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_zaiglm46_benchmarkleaderboard_284": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_zaiglm46_benchmarkleaderboard_285": { "label": "GPQA Diamond", "category": "reasoning", "score": 78, "scoreText": "78.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_artificialanalysisintelligenceindex_score_zaiglm46_benchmarkleaderboard_310": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysiscodingindex_score_zaiglm46_benchmarkleaderboard_311": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysisagenticindex_score_zaiglm46_benchmarkleaderboard_312": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." } } }, { "id": "together_ai/together_ai/zai-org/GLM-4.7", "slug": "together_ai-together_ai-zai-org-glm-4-7", "provider": "Together AI", "providerSlug": "together_ai", "name": "GLM-4.7", "displayName": "GLM-4.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.44999999999999996, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.44999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 200000, "maxInputTokens": 200000, "maxOutputTokens": 200000, "maxTokens": 200000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-04-02", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/zai-org/GLM-4.7", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/glm-4-7" }, "rawLitellm": { "input_cost_per_token": 4.5e-7, "litellm_provider": "together_ai", "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 0.000002, "source": "https://www.together.ai/models/glm-4-7", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/inference-models", "https://docs.z.ai/guides/llm/glm-4.7" ], "manual_model_modalities_note": "Together AI exact route id from official docs.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "together_ai/together_ai/moonshotai/Kimi-K2.5", "slug": "together_ai-together_ai-moonshotai-kimi-k2-5", "provider": "Together AI", "providerSlug": "together_ai", "name": "Kimi-K2.5", "displayName": "Kimi-K2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 2.8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000028 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-21", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/moonshotai/Kimi-K2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/kimi-k2-5" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "together_ai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.0000028, "source": "https://www.together.ai/models/kimi-k2-5", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/kimi-k2.5-quickstart", "https://docs.together.ai/docs/inference/vision/inputs" ], "manual_model_modalities_note": "Together AI exact route id from official multimodal docs.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "together_ai/together_ai/moonshotai/Kimi-K2-Instruct-0905", "slug": "together_ai-together_ai-moonshotai-kimi-k2-instruct-0905", "provider": "Together AI", "providerSlug": "together_ai", "name": "Kimi-K2-Instruct-0905", "displayName": "Kimi-K2-Instruct-0905", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": null, "maxInputTokens": 262144, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-03-06", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/moonshotai/Kimi-K2-Instruct-0905", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/kimi-k2-0905" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, "source": "https://www.together.ai/models/kimi-k2-0905", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.together.ai/docs/kimi-k2-quickstart", "https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905/tree/0f207df0f36ecbd273b8db0fc525b05aedd5b9ec" ], "manual_model_modalities_note": "Together AI exact route id from official docs.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." } }, { "id": "together_ai/together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct", "slug": "together_ai-together_ai-qwen-qwen3-next-80b-a3b-instruct", "provider": "Together AI", "providerSlug": "together_ai", "name": "Qwen3-Next-80B-A3B-Instruct", "displayName": "Qwen3-Next-80B-A3B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": null, "maxInputTokens": 262144, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-04-02", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://www.together.ai/models/qwen3-next-80b-a3b-instruct", "https://docs.together.ai/docs/fine-tuning-lora-supported-modules" ], "manual_model_modalities_note": "Together AI exact route id from official model page.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "together_ai/together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking", "slug": "together_ai-together_ai-qwen-qwen3-next-80b-a3b-thinking", "provider": "Together AI", "providerSlug": "together_ai", "name": "Qwen3-Next-80B-A3B-Thinking", "displayName": "Qwen3-Next-80B-A3B-Thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": null, "maxInputTokens": 262144, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-02-25", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.together.ai/docs/deprecations" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Together AI deprecations page lists this as a serverless removal date." }, "source": { "type": "litellm", "litellmKey": "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", "https://docs.together.ai/docs/fine-tuning-lora-supported-modules" ], "manual_model_modalities_note": "Together AI exact route id from official model page.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.together.ai/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "Together AI deprecations page lists this as a serverless removal date." }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "together_ai/together_ai/Qwen/Qwen3.5-397B-A17B", "slug": "together_ai-together_ai-qwen-qwen3-5-397b-a17b", "provider": "Together AI", "providerSlug": "together_ai", "name": "Qwen3.5-397B-A17B", "displayName": "Qwen3.5-397B-A17B", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3.5999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036 } }, "limits": { "contextWindow": null, "maxInputTokens": 262144, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "together_ai/Qwen/Qwen3.5-397B-A17B", "syncedAt": "2026-05-28", "sourceUrl": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000036, "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://www.together.ai/models/qwen3-5-397b-a17b", "https://docs.together.ai/docs/serverless/models" ], "manual_model_modalities_note": "Together AI exact route id from official model page." } }, { "id": "openai/tts-1", "slug": "openai-tts-1", "provider": "OpenAI", "providerSlug": "openai", "name": "tts-1", "displayName": "tts-1", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.000015, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.000015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "tts-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.000015, "litellm_provider": "openai", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "openai/tts-1-hd", "slug": "openai-tts-1-hd", "provider": "OpenAI", "providerSlug": "openai", "name": "tts-1-hd", "displayName": "tts-1-hd", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00003, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "tts-1-hd", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.00003, "litellm_provider": "openai", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "aws_polly/aws_polly/standard", "slug": "aws_polly-aws_polly-standard", "provider": "aws_polly", "providerSlug": "aws_polly", "name": "aws_polly", "displayName": "aws_polly", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.000004, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.000004 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aws_polly/standard", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/polly/pricing/" }, "rawLitellm": { "input_cost_per_character": 0.000004, "litellm_provider": "aws_polly", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/" } }, { "id": "aws_polly/aws_polly/neural", "slug": "aws_polly-aws_polly-neural", "provider": "aws_polly", "providerSlug": "aws_polly", "name": "neural", "displayName": "neural", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.000016, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.000016 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aws_polly/neural", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/polly/pricing/" }, "rawLitellm": { "input_cost_per_character": 0.000016, "litellm_provider": "aws_polly", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/" } }, { "id": "aws_polly/aws_polly/long-form", "slug": "aws_polly-aws_polly-long-form", "provider": "aws_polly", "providerSlug": "aws_polly", "name": "long-form", "displayName": "long-form", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.0001, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.0001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aws_polly/long-form", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/polly/pricing/" }, "rawLitellm": { "input_cost_per_character": 0.0001, "litellm_provider": "aws_polly", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/" } }, { "id": "aws_polly/aws_polly/generative", "slug": "aws_polly-aws_polly-generative", "provider": "aws_polly", "providerSlug": "aws_polly", "name": "generative", "displayName": "generative", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00003, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "aws_polly/generative", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/polly/pricing/" }, "rawLitellm": { "input_cost_per_character": 0.00003, "litellm_provider": "aws_polly", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/" } }, { "id": "bedrock_converse/us.amazon.nova-lite-v1:0", "slug": "bedrock_converse-us-amazon-nova-lite-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.amazon.nova-lite-v1:0", "displayName": "us.amazon.nova-lite-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.amazon.nova-lite-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-7, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-lite.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock_converse/us.amazon.nova-micro-v1:0", "slug": "bedrock_converse-us-amazon-nova-micro-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.amazon.nova-micro-v1:0", "displayName": "us.amazon.nova-micro-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.035, "outputUsdPer1MTokens": 0.14, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.035, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.4e-7 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 128000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.amazon.nova-micro-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.5e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-7, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-micro.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock_converse/us.amazon.nova-premier-v1:0", "slug": "bedrock_converse-us-amazon-nova-premier-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.amazon.nova-premier-v1:0", "displayName": "us.amazon.nova-premier-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 12.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.0000125 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 1000000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": false, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.amazon.nova-premier-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 0.0000125, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-premier.html", "https://docs.aws.amazon.com/nova/latest/userguide/additional-resources.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon route id from official docs" } }, { "id": "bedrock_converse/us.amazon.nova-pro-v1:0", "slug": "bedrock_converse-us-amazon-nova-pro-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.amazon.nova-pro-v1:0", "displayName": "us.amazon.nova-pro-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 3.1999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000032 } }, "limits": { "contextWindow": 10000, "maxInputTokens": 300000, "maxOutputTokens": 10000, "maxTokens": 10000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.amazon.nova-pro-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 0.0000032, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-pro.html" ], "manual_model_modalities_note": "Bedrock Converse exact Amazon Nova route id from official docs" } }, { "id": "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0", "slug": "bedrock-us-anthropic-claude-3-5-haiku-20241022-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.anthropic.claude-3-5-haiku-20241022-v1:0", "displayName": "us.anthropic.claude-3-5-haiku-20241022-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": 0.08, "cacheWriteUsdPer1MTokens": 1, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000001, "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-3-5-haiku-20241022-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000001, "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 8e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000004, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-5-haiku.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "aidercodeeditingleaderboard_score_claude35haiku20241022_benchmarkleaderboard_68": { "label": "Aider Code Editing", "category": "coding", "score": 75.2, "scoreText": "75.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Haiku", "exactModelOrSnapshot": "claude-3-5-haiku-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." } } }, { "id": "bedrock_converse/us.anthropic.claude-haiku-4-5-20251001-v1:0", "slug": "bedrock_converse-us-anthropic-claude-haiku-4-5-20251001-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 5.5, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": 1.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000001375, "cache_creation_input_token_cost_above_1hr": 0.0000022, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000055 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000001375, "cache_creation_input_token_cost_above_1hr": 0.0000022, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000055, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock/us.anthropic.claude-3-5-sonnet-20240620-v1:0", "slug": "bedrock-us-anthropic-claude-3-5-sonnet-20240620-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.anthropic.claude-3-5-sonnet-20240620-v1:0", "displayName": "us.anthropic.claude-3-5-sonnet-20240620-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-3-5-sonnet-20240620-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el", "https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/us.anthropic.claude-3-5-sonnet-20241022-v2:0", "slug": "bedrock-us-anthropic-claude-3-5-sonnet-20241022-v2-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", "displayName": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-region-compatibility.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock_converse/us.anthropic.claude-3-7-sonnet-20250219-v1:0", "slug": "bedrock_converse-us-anthropic-claude-3-7-sonnet-20250219-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.anthropic.claude-3-7-sonnet-20250219-v1:0", "displayName": "us.anthropic.claude-3-7-sonnet-20250219-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-3-7-sonnet-20250219-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-runtime_example_bedrock-runtime_Converse_AnthropicClaudeReasoning_section.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-region-compatibility.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock/us.anthropic.claude-3-haiku-20240307-v1:0", "slug": "bedrock-us-anthropic-claude-3-haiku-20240307-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.anthropic.claude-3-haiku-20240307-v1:0", "displayName": "us.anthropic.claude-3-haiku-20240307-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": 0.3125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-3-haiku-20240307-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 2.5e-8, "cache_creation_input_token_cost": 3.125e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." } }, { "id": "bedrock/us.anthropic.claude-3-opus-20240229-v1:0", "slug": "bedrock-us-anthropic-claude-3-opus-20240229-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.anthropic.claude-3-opus-20240229-v1:0", "displayName": "us.anthropic.claude-3-opus-20240229-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "cache_read_input_token_cost": 0.0000015, "cache_creation_input_token_cost": 0.00001875 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-3-opus-20240229-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000075, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 0.0000015, "cache_creation_input_token_cost": 0.00001875, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "aiderrefactoringleaderboard_score_claude3opus20240229_benchmarkleaderboard_69": { "label": "Aider Refactoring", "category": "coding", "score": 72.3, "scoreText": "72.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/refactor.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3 Opus", "exactModelOrSnapshot": "claude-3-opus-20240229", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Refactoring leaderboard row; diff edit format." } } }, { "id": "bedrock/us.anthropic.claude-3-sonnet-20240229-v1:0", "slug": "bedrock-us-anthropic-claude-3-sonnet-20240229-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.anthropic.claude-3-sonnet-20240229-v1:0", "displayName": "us.anthropic.claude-3-sonnet-20240229-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "pdf_input": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-3-sonnet-20240229-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html?sc_channel=el", "https://docs.aws.amazon.com/bedrock/latest/APIReference/API_GetInferenceProfile.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." } }, { "id": "bedrock_converse/us.anthropic.claude-opus-4-1-20250805-v1:0", "slug": "bedrock_converse-us-anthropic-claude-opus-4-1-20250805-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.anthropic.claude-opus-4-1-20250805-v1:0", "displayName": "us.anthropic.claude-opus-4-1-20250805-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-opus-4-1-20250805-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-1.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "bedrock_converse/us.anthropic.claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock_converse-us-anthropic-claude-sonnet-4-5-20250929-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6.6000000000000005, "above200kOutputUsdPer1MTokens": 24.75, "above200kCachedInputUsdPer1MTokens": 0.66, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_creation_input_token_cost_above_1hr": 0.0000066, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_creation_input_token_cost_above_1hr": 0.0000066, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock_converse/us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", "slug": "bedrock_converse-us-gov-anthropic-claude-sonnet-4-5-20250929-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", "displayName": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3.3000000000000003, "outputUsdPer1MTokens": 16.5, "cachedInputUsdPer1MTokens": 0.33, "cacheWriteUsdPer1MTokens": 4.125, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3.3000000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6.6000000000000005, "above200kOutputUsdPer1MTokens": 24.75, "above200kCachedInputUsdPer1MTokens": 0.66, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "output_cost_per_token": 0.0000165 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000004125, "cache_read_input_token_cost": 3.3e-7, "input_cost_per_token": 0.0000033, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000165, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "bedrock_converse/au.anthropic.claude-haiku-4-5-20251001-v1:0", "slug": "bedrock_converse-au-anthropic-claude-haiku-4-5-20251001-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 5.5, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": 1.375, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000001375, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000055 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000001375, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000055, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock_converse/us.anthropic.claude-opus-4-20250514-v1:0", "slug": "bedrock_converse-us-anthropic-claude-opus-4-20250514-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.anthropic.claude-opus-4-20250514-v1:0", "displayName": "us.anthropic.claude-opus-4-20250514-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-opus-4-20250514-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "bedrock_converse/us.anthropic.claude-opus-4-5-20251101-v1:0", "slug": "bedrock_converse-us-anthropic-claude-opus-4-5-20251101-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "us.anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.5, "outputUsdPer1MTokens": 27.5, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": 6.875, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000006875, "cache_creation_input_token_cost_above_1hr": 0.000011, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "minimal_reasoning_effort": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-opus-4-5-20251101-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000006875, "cache_creation_input_token_cost_above_1hr": 0.000011, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "bedrock_converse/global.anthropic.claude-opus-4-5-20251101-v1:0", "slug": "bedrock_converse-global-anthropic-claude-opus-4-5-20251101-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "global.anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "global.anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "minimal_reasoning_effort": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "global.anthropic.claude-opus-4-5-20251101-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic geo route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "bedrock_converse/eu.anthropic.claude-opus-4-5-20251101-v1:0", "slug": "bedrock_converse-eu-anthropic-claude-opus-4-5-20251101-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "displayName": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "minimal_reasoning_effort": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-5.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "bedrock_converse/us.anthropic.claude-sonnet-4-20250514-v1:0", "slug": "bedrock_converse-us-anthropic-claude-sonnet-4-20250514-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.anthropic.claude-sonnet-4-20250514-v1:0", "displayName": "us.anthropic.claude-sonnet-4-20250514-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.anthropic.claude-sonnet-4-20250514-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4.html" ], "manual_model_modalities_note": "Bedrock Converse exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "bedrock_converse/us.deepseek.r1-v1:0", "slug": "bedrock_converse-us-deepseek-r1-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.deepseek.r1-v1:0", "displayName": "us.deepseek.r1-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.35, "outputUsdPer1MTokens": 5.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "reasoning": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.deepseek.r1-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000135, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000054, "supports_function_calling": false, "supports_reasoning": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html" ], "manual_model_modalities_note": "Bedrock Converse exact DeepSeek geo route id from official docs" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "bedrock_converse/us.deepseek.v3.2", "slug": "bedrock_converse-us-deepseek-v3-2", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.deepseek.v3.2", "displayName": "us.deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.62, "outputUsdPer1MTokens": 1.85, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.62, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.deepseek.v3.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6.2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000185, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock_converse/eu.deepseek.v3.2", "slug": "bedrock_converse-eu-deepseek-v3-2", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "eu.deepseek.v3.2", "displayName": "eu.deepseek.v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.74, "outputUsdPer1MTokens": 2.2199999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.74, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "eu.deepseek.v3.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.4e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000222, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "bedrock/us.meta.llama3-1-405b-instruct-v1:0", "slug": "bedrock-us-meta-llama3-1-405b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.meta.llama3-1-405b-instruct-v1:0", "displayName": "us.meta.llama3-1-405b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5.32, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5.32, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000532, "output_cost_per_token": 0.000016 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.meta.llama3-1-405b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00000532, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000016, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-1-405b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "bedrock/us.meta.llama3-1-70b-instruct-v1:0", "slug": "bedrock-us-meta-llama3-1-70b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.meta.llama3-1-70b-instruct-v1:0", "displayName": "us.meta.llama3-1-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.9900000000000001, "outputUsdPer1MTokens": 0.9900000000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.9900000000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9.9e-7, "output_cost_per_token": 9.9e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.meta.llama3-1-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9.9e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 9.9e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-1-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "bedrock/us.meta.llama3-1-8b-instruct-v1:0", "slug": "bedrock-us-meta-llama3-1-8b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.meta.llama3-1-8b-instruct-v1:0", "displayName": "us.meta.llama3-1-8b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.22, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 2.2e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.meta.llama3-1-8b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.2e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 2.2e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-1-8b-instruct.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "bedrock/us.meta.llama3-2-11b-instruct-v1:0", "slug": "bedrock-us-meta-llama3-2-11b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.meta.llama3-2-11b-instruct-v1:0", "displayName": "us.meta.llama3-2-11b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 0.35, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.meta.llama3-2-11b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.5e-7, "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-11b-instruct.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "bedrock/us.meta.llama3-2-1b-instruct-v1:0", "slug": "bedrock-us-meta-llama3-2-1b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.meta.llama3-2-1b-instruct-v1:0", "displayName": "us.meta.llama3-2-1b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.meta.llama3-2-1b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.html", "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "bedrock/us.meta.llama3-2-3b-instruct-v1:0", "slug": "bedrock-us-meta-llama3-2-3b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.meta.llama3-2-3b-instruct-v1:0", "displayName": "us.meta.llama3-2-3b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.meta.llama3-2-3b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "bedrock/us.meta.llama3-2-90b-instruct-v1:0", "slug": "bedrock-us-meta-llama3-2-90b-instruct-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "us.meta.llama3-2-90b-instruct-v1:0", "displayName": "us.meta.llama3-2-90b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.meta.llama3-2-90b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-90b-instruct.html" ], "manual_model_modalities_note": "Bedrock exact geo-inference alias from official docs." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "bedrock_converse/us.meta.llama3-3-70b-instruct-v1:0", "slug": "bedrock_converse-us-meta-llama3-3-70b-instruct-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.meta.llama3-3-70b-instruct-v1:0", "displayName": "us.meta.llama3-3-70b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.meta.llama3-3-70b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-7, "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-3-70b-instruct.html" ], "manual_model_modalities_note": "Bedrock Converse exact Meta geo route id from official docs" }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "bedrock_converse/us.meta.llama4-maverick-17b-instruct-v1:0", "slug": "bedrock_converse-us-meta-llama4-maverick-17b-instruct-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.meta.llama4-maverick-17b-instruct-v1:0", "displayName": "us.meta.llama4-maverick-17b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.24, "outputUsdPer1MTokens": 0.9700000000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.24, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.12, "batchOutputUsdPer1MTokens": 0.48500000000000004, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.4e-7, "input_cost_per_token_batches": 1.2e-7, "output_cost_per_token": 9.7e-7, "output_cost_per_token_batches": 4.85e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.meta.llama4-maverick-17b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.4e-7, "input_cost_per_token_batches": 1.2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9.7e-7, "output_cost_per_token_batches": 4.85e-7, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.html" ], "manual_model_modalities_note": "Bedrock Converse exact Meta geo route id from official docs" }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "bedrock_converse/us.meta.llama4-scout-17b-instruct-v1:0", "slug": "bedrock_converse-us-meta-llama4-scout-17b-instruct-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.meta.llama4-scout-17b-instruct-v1:0", "displayName": "us.meta.llama4-scout-17b-instruct-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.16999999999999998, "outputUsdPer1MTokens": 0.66, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.16999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.08499999999999999, "batchOutputUsdPer1MTokens": 0.33, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.7e-7, "input_cost_per_token_batches": 8.5e-8, "output_cost_per_token": 6.6e-7, "output_cost_per_token_batches": 3.3e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.meta.llama4-scout-17b-instruct-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.7e-7, "input_cost_per_token_batches": 8.5e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.6e-7, "output_cost_per_token_batches": 3.3e-7, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": false, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.html" ], "manual_model_modalities_note": "Bedrock Converse exact Meta geo route id from official docs" }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "bedrock_converse/us.mistral.pixtral-large-2502-v1:0", "slug": "bedrock_converse-us-mistral-pixtral-large-2502-v1-0", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "us.mistral.pixtral-large-2502-v1:0", "displayName": "us.mistral.pixtral-large-2502-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "us.mistral.pixtral-large-2502-v1:0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000006, "supports_function_calling": true, "supports_tool_choice": false } }, { "id": "v0/v0/v0-1.0-md", "slug": "v0-v0-v0-1-0-md", "provider": "v0", "providerSlug": "v0", "name": "v0-1.0-md", "displayName": "v0-1.0-md", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "v0/v0-1.0-md", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "v0/v0/v0-1.5-lg", "slug": "v0-v0-v0-1-5-lg", "provider": "v0", "providerSlug": "v0", "name": "v0-1.5-lg", "displayName": "v0-1.5-lg", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 512000, "maxInputTokens": 512000, "maxOutputTokens": 512000, "maxTokens": 512000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "v0/v0-1.5-lg", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "litellm_provider": "v0", "max_input_tokens": 512000, "max_output_tokens": 512000, "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 0.000075, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "v0/v0/v0-1.5-md", "slug": "v0-v0-v0-1-5-md", "provider": "v0", "providerSlug": "v0", "name": "v0-1.5-md", "displayName": "v0-1.5-md", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "v0/v0-1.5-md", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/alibaba/qwen-3-14b", "slug": "vercel_ai_gateway-vercel_ai_gateway-alibaba-qwen-3-14b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "qwen-3-14b", "displayName": "qwen-3-14b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 2.4e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 40960, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/alibaba/qwen-3-14b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.4e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/qwen-3-14b", "https://vercel.com/ai-gateway/models/qwen-3-14b/about" ], "manual_model_modalities_note": "Vercel AI Gateway exact Alibaba route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/alibaba/qwen-3-235b", "slug": "vercel_ai_gateway-vercel_ai_gateway-alibaba-qwen-3-235b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "qwen-3-235b", "displayName": "qwen-3-235b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 40960, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/alibaba/qwen-3-235b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/qwen-3-235b", "https://vercel.com/ai-gateway/models/qwen-3-235b/about" ], "manual_model_modalities_note": "Vercel AI Gateway exact Alibaba route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/alibaba/qwen-3-30b", "slug": "vercel_ai_gateway-vercel_ai_gateway-alibaba-qwen-3-30b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "qwen-3-30b", "displayName": "qwen-3-30b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 40960, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/alibaba/qwen-3-30b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-7, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/qwen-3-30b", "https://vercel.com/ai-gateway/models/qwen-3-30b/about" ], "manual_model_modalities_note": "Vercel AI Gateway exact Alibaba route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/alibaba/qwen-3-32b", "slug": "vercel_ai_gateway-vercel_ai_gateway-alibaba-qwen-3-32b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "qwen-3-32b", "displayName": "qwen-3-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 40960, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/alibaba/qwen-3-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/qwen-3-32b", "https://vercel.com/ai-gateway/models/qwen-3-32b/about" ], "manual_model_modalities_note": "Vercel AI Gateway exact Alibaba route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/alibaba/qwen3-coder", "slug": "vercel_ai_gateway-vercel_ai_gateway-alibaba-qwen3-coder", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "qwen3-coder", "displayName": "qwen3-coder", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016 } }, "limits": { "contextWindow": 66536, "maxInputTokens": 262144, "maxOutputTokens": 66536, "maxTokens": 66536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/alibaba/qwen3-coder", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 262144, "max_output_tokens": 66536, "max_tokens": 66536, "mode": "chat", "output_cost_per_token": 0.0000016, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/qwen3-coder", "https://vercel.com/ai-gateway/models/qwen3-coder/about" ], "manual_model_modalities_note": "Vercel AI Gateway exact Alibaba route id from official docs" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/amazon/nova-lite", "slug": "vercel_ai_gateway-vercel_ai_gateway-amazon-nova-lite", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "nova-lite", "displayName": "nova-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.24, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 300000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/amazon/nova-lite", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-7, "supports_vision": true, "supports_function_calling": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/nova-lite", "https://docs.aws.amazon.com/ai/responsible-ai/nova-micro-lite-pro/overview.html" ], "manual_model_modalities_note": "Vercel AI Gateway exact Amazon route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/amazon/nova-micro", "slug": "vercel_ai_gateway-vercel_ai_gateway-amazon-nova-micro", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "nova-micro", "displayName": "nova-micro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.035, "outputUsdPer1MTokens": 0.14, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.035, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.4e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/amazon/nova-micro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3.5e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.4e-7, "supports_function_calling": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/nova-micro", "https://docs.aws.amazon.com/ai/responsible-ai/nova-micro-lite-pro/overview.html" ], "manual_model_modalities_note": "Vercel AI Gateway exact Amazon route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/amazon/nova-pro", "slug": "vercel_ai_gateway-vercel_ai_gateway-amazon-nova-pro", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "nova-pro", "displayName": "nova-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 3.1999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000032 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 300000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/amazon/nova-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000032, "supports_vision": true, "supports_function_calling": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/nova-pro", "https://docs.aws.amazon.com/ai/responsible-ai/nova-micro-lite-pro/overview.html" ], "manual_model_modalities_note": "Vercel AI Gateway exact Amazon route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/amazon/titan-embed-text-v2", "slug": "vercel_ai_gateway-vercel_ai_gateway-amazon-titan-embed-text-v2", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "titan-embed-text-v2", "displayName": "titan-embed-text-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 0, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "embedding", "text" ], "input": [ "text" ], "output": [ "embedding" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/amazon/titan-embed-text-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/titan-embed-text-v2", "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-text-embeddings-v2.html" ], "manual_model_modalities_note": "AWS Bedrock docs describe text input and vector-only output." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-3-haiku", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-3-haiku", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-3-haiku", "displayName": "claude-3-haiku", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": 0.3, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 3e-7, "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-3-haiku", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 3e-7, "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 2.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-3-haiku", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-3-opus", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-3-opus", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-3-opus", "displayName": "claude-3-opus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-3-opus", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000075, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-3-opus", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "aiderrefactoringleaderboard_score_claude3opus20240229_benchmarkleaderboard_69": { "label": "Aider Refactoring", "category": "coding", "score": 72.3, "scoreText": "72.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/refactor.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3 Opus", "exactModelOrSnapshot": "claude-3-opus-20240229", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Refactoring leaderboard row; diff edit format." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-3.5-haiku", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-3-5-haiku", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-3.5-haiku", "displayName": "claude-3.5-haiku", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": 0.08, "cacheWriteUsdPer1MTokens": 1, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.000001, "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-3.5-haiku", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.000001, "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 8e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000004, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-3.5-haiku", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "aidercodeeditingleaderboard_score_claude35haiku20241022_benchmarkleaderboard_68": { "label": "Aider Code Editing", "category": "coding", "score": 75.2, "scoreText": "75.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Haiku", "exactModelOrSnapshot": "claude-3-5-haiku-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-3.5-sonnet", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-3-5-sonnet", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-3.5-sonnet", "displayName": "claude-3.5-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-3.5-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-3.5-sonnet", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-3.7-sonnet", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-3-7-sonnet", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-3.7-sonnet", "displayName": "claude-3.7-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-3.7-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-3.7-sonnet", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-4-opus", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-4-opus", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-4-opus", "displayName": "claude-4-opus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-4-opus", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-opus-4", "https://platform.claude.com/docs/en/about-claude/models/overview" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-4-sonnet", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-4-sonnet", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-4-sonnet", "displayName": "claude-4-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-4-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/changelog/claude-sonnet-4-now-supports-1m-token-context-in-vercel-ai-gateway", "https://vercel.com/ai-gateway/models/claude-sonnet-4", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-3-5-sonnet", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-3-5-sonnet-2", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-3-5-sonnet", "displayName": "claude-3-5-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-3-5-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-3.5-sonnet", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-3-5-sonnet-20241022", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-3-5-sonnet-20241022", "displayName": "claude-3-5-sonnet-20241022", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-3.5-sonnet", "https://docs.anthropic.com/en/docs/about-claude/model-deprecations", "https://docs.anthropic.com/en/docs/build-with-claude/search-results", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-3-7-sonnet", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-3-7-sonnet-2", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-3-7-sonnet", "displayName": "claude-3-7-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-3-7-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-3.7-sonnet", "https://docs.anthropic.com/en/docs/about-claude/model-deprecations", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-haiku-4.5", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-haiku-4-5", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-haiku-4.5", "displayName": "claude-haiku-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": 1.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000125, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-haiku-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000125, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000005, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-haiku-4.5", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-opus-4", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-opus-4", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-opus-4", "displayName": "claude-opus-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-opus-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-opus-4", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-opus-4.1", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-opus-4-1", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-opus-4.1", "displayName": "claude-opus-4.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-opus-4.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-opus-4.1", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-opus-4.5", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-opus-4-5", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-opus-4.5", "displayName": "claude-opus-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "minimal_reasoning_effort": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-opus-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_minimal_reasoning_effort": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-opus-4.5", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-opus-4.6", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-opus-4-6", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-opus-4.6", "displayName": "claude-opus-4.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-opus-4.6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_minimal_reasoning_effort": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-opus-4.6", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-sonnet-4", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-sonnet-4", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-sonnet-4", "displayName": "claude-sonnet-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-sonnet-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-sonnet-4", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/anthropic/claude-sonnet-4.5", "slug": "vercel_ai_gateway-vercel_ai_gateway-anthropic-claude-sonnet-4-5", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "claude-sonnet-4.5", "displayName": "claude-sonnet-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "file", "image", "text" ], "input": [ "file", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/anthropic/claude-sonnet-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/claude-sonnet-4.5", "https://docs.anthropic.com/en/docs/about-claude/models/overview", "https://docs.anthropic.com/en/docs/build-with-claude/vision" ], "manual_model_modalities_note": "Vercel AI Gateway exact Anthropic route id from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/cohere/command-a", "slug": "vercel_ai_gateway-vercel_ai_gateway-cohere-command-a", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "command-a", "displayName": "command-a", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 256000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/cohere/command-a", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/command-a", "https://docs.cohere.com/docs/models" ], "manual_model_modalities_note": "Vercel AI Gateway exact Cohere route id from official docs" }, "benchmarks": { "mmlu_accuracy_commanda_paper_130": { "label": "MMLU", "category": "general_knowledge", "score": 85.5, "scoreText": "85.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "mmlupro_accuracy_commanda_paper_131": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "gpqa_accuracy_commanda_paper_132": { "label": "GPQA", "category": "general_knowledge", "score": 50.8, "scoreText": "50.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; academic benchmark results for Command A." }, "ifeval_strictaccuracy_commanda_paper_133": { "label": "IFEval", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "strict accuracy", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3 in the official technical report; instruction-following benchmark for Command A." }, "bfcloverall_score_commanda_paper_134": { "label": "BFCL", "category": "agentic", "score": 63.8, "scoreText": "63.8", "metric": "score", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 5 in the official technical report; BFCL values are taken from the official leaderboard." }, "taubenchretail_pass1_commanda_paper_135": { "label": "Taubench Retail", "category": "agentic", "score": 60, "scoreText": "P@1 60.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." }, "taubenchairline_pass1_commanda_paper_136": { "label": "Taubench Airline", "category": "agentic", "score": 45.3, "scoreText": "P@1 45.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://cohere.com/research/papers/command-a-technical-report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "command-a", "exactModelOrSnapshot": "Command A", "modelDeveloper": "Cohere", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 6 in the official technical report; pass@k scores are aggregated over 10 runs." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/cohere/command-r", "slug": "vercel_ai_gateway-vercel_ai_gateway-cohere-command-r", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "command-r", "displayName": "command-r", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/cohere/command-r", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cohere.com/v1/docs/command-r", "https://docs.cohere.com/docs/models" ], "manual_model_modalities_note": "Vercel AI Gateway exact Cohere route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/cohere/command-r-plus", "slug": "vercel_ai_gateway-vercel_ai_gateway-cohere-command-r-plus", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "command-r-plus", "displayName": "command-r-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/cohere/command-r-plus", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cohere.com/v2/docs/command-r-plus", "https://docs.cohere.com/docs/models" ], "manual_model_modalities_note": "Vercel AI Gateway exact Cohere route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/cohere/embed-v4.0", "slug": "vercel_ai_gateway-vercel_ai_gateway-cohere-embed-v4-0", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "embed-v4.0", "displayName": "embed-v4.0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 0, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "embedding", "image", "pdf", "text" ], "input": [ "image", "pdf", "text" ], "output": [ "embedding" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/cohere/embed-v4.0", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/embed-v4.0", "https://docs.cohere.com/docs/cohere-embed" ], "manual_model_modalities_note": "Cohere docs list embed-v4.0 as supporting text, image, and PDF-style mixed inputs with embedding output." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/deepseek/deepseek-r1", "slug": "vercel_ai_gateway-vercel_ai_gateway-deepseek-deepseek-r1", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "deepseek-r1", "displayName": "deepseek-r1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.55, "outputUsdPer1MTokens": 2.1900000000000004, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.55, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/deepseek/deepseek-r1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000219, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/deepseek-r1", "https://api-docs.deepseek.com/guides/reasoning_model" ], "manual_model_modalities_note": "Vercel AI Gateway exact DeepSeek route id from official docs" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b", "slug": "vercel_ai_gateway-vercel_ai_gateway-deepseek-deepseek-r1-distill-llama-70b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "deepseek-r1-distill-llama-70b", "displayName": "deepseek-r1-distill-llama-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.75, "outputUsdPer1MTokens": 0.9900000000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.5e-7, "output_cost_per_token": 9.9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 9.9e-7, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/docs/agent-resources/integrations-for-models/deepinfra" ], "manual_model_modalities_note": "Vercel Deep Infra integration lists this as a chat/text generation model." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/deepseek/deepseek-v3", "slug": "vercel_ai_gateway-vercel_ai_gateway-deepseek-deepseek-v3", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "deepseek-v3", "displayName": "deepseek-v3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/deepseek/deepseek-v3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/deepseek-v3", "https://api-docs.deepseek.com/zh-cn/news/news1226" ], "manual_model_modalities_note": "DeepSeek V3 release note says the current version does not support multimodal input/output." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/google/gemini-2.0-flash", "slug": "vercel_ai_gateway-vercel_ai_gateway-google-gemini-2-0-flash", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gemini-2.0-flash", "displayName": "gemini-2.0-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "image", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01" }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/google/gemini-2.0-flash", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-06-01", "input_cost_per_token": 1.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-7, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/gemini-2.0-flash" ], "manual_model_modalities_note": "Vercel AI Gateway exact Gemini route id from official docs" }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/google/gemini-2.0-flash-lite", "slug": "vercel_ai_gateway-vercel_ai_gateway-google-gemini-2-0-flash-lite", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gemini-2.0-flash-lite", "displayName": "gemini-2.0-flash-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01" }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/google/gemini-2.0-flash-lite", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-06-01", "input_cost_per_token": 7.5e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-7, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/gemini-2.0-flash-lite", "https://ai.google.dev/gemini-api/docs/models/gemini-v2" ], "manual_model_modalities_note": "Google docs list audio, image, video, and text inputs with text output." }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "mmlupro_accuracy_gemini20flashlitepublicpreview_officialmodelcard_79": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashlitepublicpreview_officialmodelcard_80": { "label": "LiveCodeBench v5", "category": "coding", "score": 28.9, "scoreText": "28.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashlitepublicpreview_officialmodelcard_81": { "label": "GPQA Diamond", "category": "science", "score": 51.5, "scoreText": "51.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "math_accuracy_gemini20flashlitepublicpreview_officialmodelcard_82": { "label": "MATH", "category": "math", "score": 86.8, "scoreText": "86.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashlitepublicpreview_officialmodelcard_83": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/google/gemini-2.5-flash", "slug": "vercel_ai_gateway-vercel_ai_gateway-google-gemini-2-5-flash", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gemini-2.5-flash", "displayName": "gemini-2.5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1000000, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/google/gemini-2.5-flash", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000025, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/gemini-2.5-flash", "https://ai.google.dev/gemini-api/docs/models/gemini" ], "manual_model_modalities_note": "Vercel AI Gateway exact Gemini route id from official docs" } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/google/gemini-2.5-pro", "slug": "vercel_ai_gateway-vercel_ai_gateway-google-gemini-2-5-pro", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gemini-2.5-pro", "displayName": "gemini-2.5-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/google/gemini-2.5-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.00001, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/gemini-2.5-pro", "https://ai.google.dev/gemini-api/docs/models/gemini-v2" ], "manual_model_modalities_note": "Google docs list audio, image, video, text, and PDF inputs with text output." }, "benchmarks": { "humanityslastexam_accuracy_gemini25proga_officialmodelcard_84": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 21.6, "scoreText": "21.6% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "gpqadiamond_pass1_gemini25proga_officialmodelcard_85": { "label": "GPQA Diamond", "category": "science", "score": 86.4, "scoreText": "86.4% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aime2025_pass1_gemini25proga_officialmodelcard_86": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0% pass@1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "livecodebench_accuracy_gemini25proga_officialmodelcard_87": { "label": "LiveCodeBench", "category": "coding", "score": 69, "scoreText": "69.0% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; LiveCodeBench window is 1/1/2025-5/1/2025." }, "aiderpolyglot_passrate_gemini25proga_officialmodelcard_88": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2% diff-fenced", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table; evaluation settings differ from the public leaderboard." }, "swebenchverified_accuracy_gemini25proga_officialmodelcard_89": { "label": "SWE-bench Verified", "category": "agentic", "score": 59.6, "scoreText": "59.6% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Pro-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "Gemini 2.5 Pro (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the June 2025 model card table." }, "aiderpolyglot_passrate_gemini25pro_paper_286": { "label": "Aider Polyglot", "category": "coding", "score": 82.2, "scoreText": "82.2%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "swebenchverifiedmultipleattempts_accuracy_gemini25pro_paper_287": { "label": "SWE-bench Verified (multiple attempts)", "category": "coding", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "gpqa_accuracy_gemini25pro_paper_288": { "label": "GPQA", "category": "reasoning", "score": 86.4, "scoreText": "86.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. Table 4 compares Gemini 2.5 Pro against other large models; this is the Gemini 2.5 Pro column." }, "aime2025_accuracy_gemini25pro_paper_289": { "label": "AIME 2025", "category": "math", "score": 88, "scoreText": "88.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf?file=gemini_v2_5_report.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro", "exactModelOrSnapshot": "gemini-2.5-pro", "modelDeveloper": "Google DeepMind", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Gemini 2.5 report. The report text states Gemini 2.5 Pro scores 88.0% on AIME 2025." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0605_benchmarkleaderboard_223": { "label": "Aider Polyglot", "category": "coding", "score": 79.1, "scoreText": "79.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-06-05", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row; source shows the default-think variant." }, "aiderpolyglot_percentcorrect_geminigemini25propreview0506_benchmarkleaderboard_224": { "label": "Aider Polyglot", "category": "coding", "score": 76.9, "scoreText": "76.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.5 Pro Preview", "exactModelOrSnapshot": "gemini/gemini-2.5-pro-preview-05-06", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the preview snapshot." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/google/gemini-embedding-001", "slug": "vercel_ai_gateway-vercel_ai_gateway-google-gemini-embedding-001", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gemini-embedding-001", "displayName": "gemini-embedding-001", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 0, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/google/gemini-embedding-001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/google/gemma-2-9b", "slug": "vercel_ai_gateway-vercel_ai_gateway-google-gemma-2-9b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gemma-2-9b", "displayName": "gemma-2-9b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/google/gemma-2-9b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-7, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemma/docs/core/model_card_2", "https://huggingface.co/google/gemma-2-9b-it" ], "manual_model_modalities_note": "Gemma 2 docs define text input and text output." }, "benchmarks": { "mmlu_5shottop1_gemma2pt27b_officialmodelcard_189": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "hellaswag_10shot_gemma2pt27b_officialmodelcard_190": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "humaneval_pass1_gemma2pt27b_officialmodelcard_191": { "label": "HumanEval", "category": "coding", "score": 51.8, "scoreText": "51.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "gsm8k_5shotmaj1_gemma2pt27b_officialmodelcard_192": { "label": "GSM8K", "category": "math", "score": 74, "scoreText": "74.0", "metric": "5-shot, maj@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mmlu_5shottop1_gemmapt27b_officialmodelcard_23": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_hellaswag_10shot_gemmapt27b_officialmodelcard_24": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_arcc_25shot_gemmapt27b_officialmodelcard_25": { "label": "ARC-Challenge", "category": "reasoning", "score": 71.4, "scoreText": "71.4", "metric": "25-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_triviaqa_5shot_gemmapt27b_officialmodelcard_26": { "label": "TriviaQA", "category": "general_knowledge", "score": 83.7, "scoreText": "83.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_realtoxicity_average_gemma2it27b_officialmodelcard_27": { "label": "RealToxicity", "category": "safety", "score": 8.84, "scoreText": "8.84", "metric": "average", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." }, "local_truthfulqa_score_gemma2it27b_officialmodelcard_28": { "label": "TruthfulQA", "category": "safety", "score": 51.6, "scoreText": "51.60", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/google/text-embedding-005", "slug": "vercel_ai_gateway-vercel_ai_gateway-google-text-embedding-005", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "text-embedding-005", "displayName": "text-embedding-005", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.024999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.024999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 0, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/google/text-embedding-005", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/google/text-multilingual-embedding-002", "slug": "vercel_ai_gateway-vercel_ai_gateway-google-text-multilingual-embedding-002", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "text-multilingual-embedding-002", "displayName": "text-multilingual-embedding-002", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.024999999999999998, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.024999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 0, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/google/text-multilingual-embedding-002", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/inception/mercury-coder-small", "slug": "vercel_ai_gateway-vercel_ai_gateway-inception-mercury-coder-small", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "mercury-coder-small", "displayName": "mercury-coder-small", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 32000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/inception/mercury-coder-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000001, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/mercury-coder-small", "https://vercel.com/ai-gateway/models/mercury-coder-small/about" ], "manual_model_modalities_note": "Vercel describes Mercury Coder Small as a coding model for text/code prompts." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-3-70b", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-3-70b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-3-70b", "displayName": "llama-3-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.59, "outputUsdPer1MTokens": 0.7899999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.59, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.9e-7, "output_cost_per_token": 7.9e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-3-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5.9e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.9e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct", "https://vercel.com/ai-gateway/models/llama-3-70b" ], "manual_model_modalities_note": "Meta Llama 3 70B Instruct docs define text input with text/code output." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-3-8b", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-3-8b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-3-8b", "displayName": "llama-3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-8, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct", "https://vercel.com/ai-gateway/models/llama-3-8b" ], "manual_model_modalities_note": "Meta Llama 3 8B Instruct docs define text input with text/code output." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-3.1-70b", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-3-1-70b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-3.1-70b", "displayName": "llama-3.1-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-3.1-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/llama-3.1-70b", "https://vercel.com/ai-gateway/models/llama-3.1-8b/faq" ], "manual_model_modalities_note": "Vercel Llama 3.1 family note says no model supports vision input." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-3.1-8b", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-3-1-8b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-3.1-8b", "displayName": "llama-3.1-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131000, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-3.1-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-8, "supports_function_calling": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/llama-3.1-8b", "https://vercel.com/ai-gateway/models/llama-3.1-8b/faq" ], "manual_model_modalities_note": "Vercel says no Llama 3.1 model supports vision input." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-3.2-11b", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-3-2-11b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-3.2-11b", "displayName": "llama-3.2-11b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.16, "outputUsdPer1MTokens": 0.16, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.16, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.6e-7, "output_cost_per_token": 1.6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-3.2-11b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.6e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.6e-7, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/llama-3.2-11b", "https://examples.vercel.com/ai-gateway/models/llama-3.2-11b" ], "manual_model_modalities_note": "Official page describes this as text + images in and text out." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-3.2-1b", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-3-2-1b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-3.2-1b", "displayName": "llama-3.2-1b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-3.2-1b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-7, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/llama-3.2-1b", "https://vercel.com/ai-gateway/models/llama-3.2-1b/about" ], "manual_model_modalities_note": "Official page says the 1B model is text-only." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-3.2-3b", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-3-2-3b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-3.2-3b", "displayName": "llama-3.2-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-3.2-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-7, "supports_function_calling": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/llama-3.2-3b", "https://vercel.com/ai-gateway/models/llama-3.2-3b/about" ], "manual_model_modalities_note": "Official page says the 3B model is text-only." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-3.2-90b", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-3-2-90b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-3.2-90b", "displayName": "llama-3.2-90b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-3.2-90b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-7, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/llama-3.2-90b", "https://vercel.com/ai-gateway/models/llama-3.2-90b/about" ], "manual_model_modalities_note": "Official page describes this as a vision-language model with text output." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-3.3-70b", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-3-3-70b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-3.3-70b", "displayName": "llama-3.3-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.72, "outputUsdPer1MTokens": 0.72, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.72, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-3.3-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.2e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-7, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/llama-3.3-70b", "https://vercel.com/ai-gateway/models/llama-3.3-70b/about" ], "manual_model_modalities_note": "Official page says this model is text-only." }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-4-maverick", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-4-maverick", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-4-maverick", "displayName": "llama-4-maverick", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-4-maverick", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-7, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/llama-4-maverick", "https://vercel.com/ai-gateway/models/llama-4-maverick/about" ], "manual_model_modalities_note": "Official page describes this model as natively multimodal." }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/meta/llama-4-scout", "slug": "vercel_ai_gateway-vercel_ai_gateway-meta-llama-4-scout", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "llama-4-scout", "displayName": "llama-4-scout", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/meta/llama-4-scout", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-7, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/llama-4-scout", "https://ai.meta.com/blog/llama-4-multimodal-intelligence/" ], "manual_model_modalities_note": "Vercel labels this model Vision (Image); Meta describes Llama 4 Scout as natively multimodal." }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/codestral", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-codestral", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "codestral", "displayName": "codestral", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 256000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/codestral", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-7, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/codestral", "https://docs.mistral.ai/capabilities/code_generation" ], "manual_model_modalities_note": "Official docs describe Codestral as a code generation/FIM text model." }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/codestral-embed", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-codestral-embed", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "codestral-embed", "displayName": "codestral-embed", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 0, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "embedding", "text" ], "input": [ "text" ], "output": [ "embedding" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/codestral-embed", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/codestral-embed", "https://docs.mistral.ai/resources/cookbooks/mistral-embeddings-code_embedding" ], "manual_model_modalities_note": "Official docs describe Codestral Embed as a code embedding model." }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/devstral-small", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-devstral-small", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "devstral-small", "displayName": "devstral-small", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/devstral-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-7, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/devstral-small", "https://docs.mistral.ai/capabilities/code_generation" ], "manual_model_modalities_note": "Official docs describe Devstral Small as a text model for tool use and software engineering." }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/magistral-medium", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-magistral-medium", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "magistral-medium", "displayName": "magistral-medium", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/magistral-medium", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000005, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/magistral-medium", "https://vercel.com/ai-gateway/models/magistral-medium/about" ], "manual_model_modalities_note": "Model page labels this as Reasoning Vision (Image); output is text." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/magistral-small", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-magistral-small", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "magistral-small", "displayName": "magistral-small", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 128000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/magistral-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/magistral-small", "https://vercel.com/ai-gateway/models/magistral-small/about" ], "manual_model_modalities_note": "Model page labels this as Reasoning Vision (Image); output is text." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/ministral-3b", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-ministral-3b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "ministral-3b", "displayName": "ministral-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.04, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/ministral-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-8, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/ministral-3b", "https://vercel.com/ai-gateway/models/ministral-3b/about" ], "manual_model_modalities_note": "Model page says image understanding belongs to Ministral 14B, so this id is text-only." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/ministral-8b", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-ministral-8b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "ministral-8b", "displayName": "ministral-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/ministral-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-7, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/ministral-8b" ], "manual_model_modalities_note": "No vision modality is listed on the model page." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/mistral-embed", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-mistral-embed", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "mistral-embed", "displayName": "mistral-embed", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 0, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "embedding", "text" ], "input": [ "text" ], "output": [ "embedding" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/mistral-embed", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/mistral-embed/about" ], "manual_model_modalities_note": "Text embedding model." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/mistral-large", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-mistral-large", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "mistral-large", "displayName": "mistral-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 32000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/mistral-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.000006, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.mistral.ai/models/mistral-large-3-25-12", "https://docs.mistral.ai/capabilities/vision" ], "manual_model_modalities_note": "Mistral docs define Mistral Large 3 as multimodal and list it in the vision-capable chat models." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/mistral-saba-24b", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-mistral-saba-24b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "mistral-saba-24b", "displayName": "mistral-saba-24b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7899999999999999, "outputUsdPer1MTokens": 0.7899999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7899999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.9e-7, "output_cost_per_token": 7.9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/mistral-saba-24b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.9e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.9e-7 } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/mistral-small", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-mistral-small", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "mistral-small", "displayName": "mistral-small", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 32000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/mistral-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/mistral-small" ], "manual_model_modalities_note": "Tool use and vision are listed on the model page." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/mixtral-8x22b-instruct", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-mixtral-8x22b-instruct", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "mixtral-8x22b-instruct", "displayName": "mixtral-8x22b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 65536, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/mixtral-8x22b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000012, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 65536, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/mixtral-8x22b-instruct" ], "manual_model_modalities_note": "Native function calling is documented; no vision modality is listed." }, "benchmarks": { "gsm8kmaj8_8shot_mixtral8x22binstruct_officiallaunchpost_212": { "label": "GSM8K maj@8", "category": "math", "score": 90.8, "scoreText": "90.8%", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on GSM8K maj@8." }, "mathmaj4_4shot_mixtral8x22binstruct_officiallaunchpost_213": { "label": "Math maj@4", "category": "math", "score": 44.6, "scoreText": "44.6%", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on Math maj@4." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/pixtral-12b", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-pixtral-12b", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "pixtral-12b", "displayName": "pixtral-12b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/pixtral-12b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-7, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/pixtral-12b/about", "https://docs.mistral.ai/models/pixtral-12b-24-09" ], "manual_model_modalities_note": "Mistral docs describe image understanding in addition to text." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/mistral/pixtral-large", "slug": "vercel_ai_gateway-vercel_ai_gateway-mistral-pixtral-large", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "pixtral-large", "displayName": "pixtral-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 128000, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/mistral/pixtral-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.000006, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/pixtral-large/about", "https://docs.mistral.ai/models/pixtral-large-24-11" ], "manual_model_modalities_note": "Mistral docs describe this as a multimodal model with image understanding and text output." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/moonshotai/kimi-k2", "slug": "vercel_ai_gateway-vercel_ai_gateway-moonshotai-kimi-k2", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "kimi-k2", "displayName": "kimi-k2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.55, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.55, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 131072, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/moonshotai/kimi-k2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000022, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/kimi-k2/faq", "https://platform.moonshot.ai/docs/pricing/chat" ], "manual_model_modalities_note": "Moonshot docs say Kimi K2 is a generation model and does not support vision; Vercel FAQ says it is text-only." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/morph/morph-v3-fast", "slug": "vercel_ai_gateway-vercel_ai_gateway-morph-morph-v3-fast", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "morph-v3-fast", "displayName": "morph-v3-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 32768, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/morph/morph-v3-fast", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 8e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000012, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/morph-v3-fast/about", "https://docs.morphllm.com/models/apply" ], "manual_model_modalities_note": "Morph describes this as a code-editing model that takes text/code input and returns merged code." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/morph/morph-v3-large", "slug": "vercel_ai_gateway-vercel_ai_gateway-morph-morph-v3-large", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "morph-v3-large", "displayName": "morph-v3-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 1.9, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 0.0000019 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 32768, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/morph/morph-v3-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 9e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000019, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/morph-v3-large/providers", "https://docs.morphllm.com/models/apply" ], "manual_model_modalities_note": "Morph describes this as a code-editing model that takes text/code input and returns merged code." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/gpt-3.5-turbo", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-gpt-3-5-turbo", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gpt-3.5-turbo", "displayName": "gpt-3.5-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16385, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/gpt-3.5-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://platform.openai.com/docs/models/gpt-3.5-turbo" ], "manual_model_modalities_note": "OpenAI lists text as the supported modality." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/gpt-3.5-turbo-instruct", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-gpt-3-5-turbo-instruct", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gpt-3.5-turbo-instruct", "displayName": "gpt-3.5-turbo-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.5, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 8192, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000015, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000002, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/gpt-3.5-turbo-instruct/about", "https://platform.openai.com/docs/models/gpt-3.5-turbo-instruct" ], "manual_model_modalities_note": "OpenAI docs list text input and text output only." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/gpt-4-turbo", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-gpt-4-turbo", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gpt-4-turbo", "displayName": "gpt-4-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10, "outputUsdPer1MTokens": 30, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/gpt-4-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.00001, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/gpt-4-turbo", "https://platform.openai.com/docs/models/gpt-4-turbo" ], "manual_model_modalities_note": "OpenAI docs list text and image input with text output." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/gpt-4.1", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-gpt-4-1", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gpt-4.1", "displayName": "gpt-4.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/gpt-4.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000008, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/gpt-4.1", "https://platform.openai.com/docs/models/gpt-4.1" ], "manual_model_modalities_note": "OpenAI docs list text and image input with text output." }, "benchmarks": { "swebenchverified_accuracy_gpt41_officiallaunchpost_0": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table; GPT-4.1 versus GPT-4o(2024-11-20), GPT-4o mini, o1(high), and o3-mini(high)." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_1": { "label": "Aider Polyglot", "category": "coding", "score": 51.6, "scoreText": "51.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the appendix comparison table." }, "aiderpolyglot_accuracy_gpt41_officiallaunchpost_2": { "label": "Aider Polyglot", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the appendix comparison table." }, "ifeval_accuracy_gpt41_officiallaunchpost_3": { "label": "IFEval", "category": "agentic", "score": 87.4, "scoreText": "87.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following score from the appendix comparison table." }, "openaimrcr2needle128k_accuracy_gpt41_officiallaunchpost_4": { "label": "OpenAI-MRCR: 2 needle 128k", "category": "long_context", "score": 57.2, "scoreText": "57.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1", "exactModelOrSnapshot": "GPT-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context retrieval score from the appendix comparison table." }, "swebenchverified_accuracy_gpt41_officiallaunchpost_254": { "label": "SWE-bench Verified", "category": "coding", "score": 54.6, "scoreText": "54.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is shown in the coding eval table." }, "multichallenge_accuracy_gpt41_officiallaunchpost_255": { "label": "MultiChallenge", "category": "other", "score": 38.3, "scoreText": "38.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Instruction-following benchmark; exact value is in the launch table." }, "videommelongnosubtitles_accuracy_gpt41_officiallaunchpost_256": { "label": "Video-MME", "category": "multimodal", "score": 72, "scoreText": "72.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Multimodal long-context benchmark, exact value shown in the long-context section." }, "aiderpolyglotdiff_passrate_gpt41_officiallaunchpost_257": { "label": "Aider Polyglot Diff", "category": "coding", "score": 52.9, "scoreText": "52.9%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1", "exactModelOrSnapshot": "gpt-4.1", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Diff-format coding benchmark from the coding eval table." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/gpt-4.1-mini", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-gpt-4-1-mini", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gpt-4.1-mini", "displayName": "gpt-4.1-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.5999999999999999, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/gpt-4.1-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 4e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000016, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/gpt-4.1-mini", "https://platform.openai.com/docs/models/gpt-4.1-mini" ], "manual_model_modalities_note": "OpenAI docs list text and image input with text output." }, "benchmarks": { "swebenchverified_accuracy_gpt41mini_officiallaunchpost_5": { "label": "SWE-bench Verified", "category": "coding", "score": 23.6, "scoreText": "23.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-mini", "exactModelOrSnapshot": "GPT-4.1 mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table for the GPT-4.1 family." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/gpt-4.1-nano", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-gpt-4-1-nano", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gpt-4.1-nano", "displayName": "gpt-4.1-nano", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 1047576, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/gpt-4.1-nano", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 1e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-7, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/gpt-4.1-nano", "https://platform.openai.com/docs/models/gpt-4.1-nano" ], "manual_model_modalities_note": "OpenAI docs list text and image input with text output." }, "benchmarks": { "aime24_accuracy_gpt41nano_officiallaunchpost_6": { "label": "AIME 2024", "category": "reasoning", "score": 29.4, "scoreText": "29.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4.1-nano", "exactModelOrSnapshot": "GPT-4.1 nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Academic-knowledge appendix comparison row for the nano model." }, "mmlu_accuracy_gpt41nano_officiallaunchpost_258": { "label": "MMLU", "category": "general_knowledge", "score": 80.1, "scoreText": "80.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the narrative and table." }, "gpqa_accuracy_gpt41nano_officiallaunchpost_259": { "label": "GPQA", "category": "reasoning", "score": 50.3, "scoreText": "50.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." }, "aiderpolyglotcoding_passrate_gpt41nano_officiallaunchpost_260": { "label": "Aider Polyglot", "category": "coding", "score": 9.8, "scoreText": "9.8%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4.1 nano", "exactModelOrSnapshot": "gpt-4.1-nano", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact nano score is stated in the launch text." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/gpt-4o", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-gpt-4o", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gpt-4o", "displayName": "gpt-4o", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/gpt-4o", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/gpt-4o", "https://platform.openai.com/docs/models/gpt-4o" ], "manual_model_modalities_note": "OpenAI docs list text and image input with text output." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/gpt-4o-mini", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-gpt-4o-mini", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "gpt-4o-mini", "displayName": "gpt-4o-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 128000, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/gpt-4o-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-7, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://platform.openai.com/docs/models/gpt-4o-mini", "https://examples.vercel.com/ai-gateway/models/gpt-4o-mini" ], "manual_model_modalities_note": "OpenAI docs confirm text/image input with text output." }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/o1", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-o1", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "openai", "displayName": "openai", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 60, "cachedInputUsdPer1MTokens": 7.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/o1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00006, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/o1", "https://developers.openai.com/api/docs/models/o1" ], "manual_model_modalities_note": "OpenAI docs list text/image input with text output." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/o3", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-o3", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "openai", "displayName": "openai", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/o3", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000008, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/o3", "https://developers.openai.com/api/docs/models/o3" ], "manual_model_modalities_note": "OpenAI docs list text/image input with text output." }, "benchmarks": { "aime2025_accuracy_openaio3high_officiallaunchpost_12": { "label": "AIME 2025", "category": "reasoning", "score": 88.9, "scoreText": "88.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio3high_officiallaunchpost_13": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio3high_officiallaunchpost_14": { "label": "SWE-bench Verified", "category": "coding", "score": 69.1, "scoreText": "69.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o3", "exactModelOrSnapshot": "OpenAI o3 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/o3-mini", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-o3-mini", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "o3-mini", "displayName": "o3-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.55, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/o3-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/o3-mini", "https://developers.openai.com/api/docs/models/o3-mini" ], "manual_model_modalities_note": "OpenAI docs list text input/output and image not supported." }, "benchmarks": { "aime2024_accuracy_o3minihigh_officiallaunchpost_18": { "label": "AIME 2024", "category": "reasoning", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "gpqadiamond_accuracy_o3minihigh_officiallaunchpost_19": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 77, "scoreText": "77.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; high reasoning effort." }, "swebenchverified_accuracy_o3minihigh_officiallaunchpost_20": { "label": "SWE-bench Verified", "category": "coding", "score": 48.9, "scoreText": "48.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/openai-o3-mini/", "checked_at": "2026-05-31", "baseModelFamily": "o3-mini", "exactModelOrSnapshot": "o3-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Launch post chart callout; n=477 verified tasks." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/o4-mini", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-o4-mini", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "o4-mini", "displayName": "o4-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.4, "cachedInputUsdPer1MTokens": 0.275, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.75e-7, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044 } }, "limits": { "contextWindow": 100000, "maxInputTokens": 200000, "maxOutputTokens": 100000, "maxTokens": 100000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/o4-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.75e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/o4-mini", "https://developers.openai.com/api/docs/models/o4-mini" ], "manual_model_modalities_note": "OpenAI docs list text/image input with text output." }, "benchmarks": { "aime2025_accuracy_openaio4minihigh_officiallaunchpost_15": { "label": "AIME 2025", "category": "reasoning", "score": 92.7, "scoreText": "92.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "gpqadiamond_accuracy_openaio4minihigh_officiallaunchpost_16": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 81.4, "scoreText": "81.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "swebenchverified_accuracy_openaio4minihigh_officiallaunchpost_17": { "label": "SWE-bench Verified", "category": "coding", "score": 68.1, "scoreText": "68.1%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "o4-mini", "exactModelOrSnapshot": "OpenAI o4-mini (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/text-embedding-3-large", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-text-embedding-3-large", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "text-embedding-3-large", "displayName": "text-embedding-3-large", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 0, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/text-embedding-3-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.3e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/text-embedding-3-small", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-text-embedding-3-small", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "text-embedding-3-small", "displayName": "text-embedding-3-small", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 0, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/text-embedding-3-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/openai/text-embedding-ada-002", "slug": "vercel_ai_gateway-vercel_ai_gateway-openai-text-embedding-ada-002", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "text-embedding-ada-002", "displayName": "text-embedding-ada-002", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 0, "maxInputTokens": 0, "maxOutputTokens": 0, "maxTokens": 0, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/openai/text-embedding-ada-002", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/perplexity/sonar", "slug": "vercel_ai_gateway-vercel_ai_gateway-perplexity-sonar", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "sonar", "displayName": "sonar", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 127000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/perplexity/sonar", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.000001 } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/perplexity/sonar-pro", "slug": "vercel_ai_gateway-vercel_ai_gateway-perplexity-sonar-pro", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "sonar-pro", "displayName": "sonar-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 200000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/perplexity/sonar-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.000015, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.perplexity.ai/docs/sonar/models/sonar-pro", "https://docs.perplexity.ai/docs/sonar/media" ], "manual_model_modalities_note": "Perplexity docs show sonar-pro in the image-input API examples and return text content." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/perplexity/sonar-reasoning", "slug": "vercel_ai_gateway-vercel_ai_gateway-perplexity-sonar-reasoning", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "sonar-reasoning", "displayName": "sonar-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 127000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/perplexity/sonar-reasoning", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.000005 } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/perplexity/sonar-reasoning-pro", "slug": "vercel_ai_gateway-vercel_ai_gateway-perplexity-sonar-reasoning-pro", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "sonar-reasoning-pro", "displayName": "sonar-reasoning-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 127000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/perplexity/sonar-reasoning-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.000008, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/sonar-reasoning-pro", "https://vercel.com/ai-gateway/models/sonar-reasoning-pro/about" ], "manual_model_modalities_note": "No vision modality is shown in the official docs." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/vercel/v0-1.0-md", "slug": "vercel_ai_gateway-vercel_ai_gateway-vercel-v0-1-0-md", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "v0-1.0-md", "displayName": "v0-1.0-md", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 128000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/vercel/v0-1.0-md", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/v0-1.0-md", "https://vercel.com/ai-gateway/models?type=image" ], "manual_model_modalities_note": "Official docs label this model as Vision (Image)." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/vercel/v0-1.5-md", "slug": "vercel_ai_gateway-vercel_ai_gateway-vercel-v0-1-5-md", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "v0-1.5-md", "displayName": "v0-1.5-md", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 128000, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/vercel/v0-1.5-md", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000015, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/v0-1.5-md/faq", "https://vercel.com/ai-gateway/models?type=image" ], "manual_model_modalities_note": "Official docs label this model as Vision (Image)." } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/xai/grok-2", "slug": "vercel_ai_gateway-vercel_ai_gateway-xai-grok-2", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "grok-2", "displayName": "grok-2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 131072, "maxOutputTokens": 4000, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/xai/grok-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models?provider=xai", "https://vercel.com/docs/agent-resources/integrations-for-models/xai" ], "manual_model_modalities_note": "xAI docs list Grok-2 as Type: Chat." }, "benchmarks": { "gpqa_accuracy_grok2_officiallaunchpost_105": { "label": "GPQA", "category": "general_knowledge", "score": 56, "scoreText": "56.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlu_accuracy_grok2_officiallaunchpost_106": { "label": "MMLU", "category": "general_knowledge", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlupro_accuracy_grok2_officiallaunchpost_107": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "math_accuracy_grok2_officiallaunchpost_108": { "label": "MATH", "category": "math", "score": 76.1, "scoreText": "76.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "humaneval_pass1_grok2_officiallaunchpost_109": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 HumanEval is reported as pass@1." }, "mmmu_accuracy_grok2_officiallaunchpost_110": { "label": "MMMU", "category": "multimodal", "score": 66.1, "scoreText": "66.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/xai/grok-2-vision", "slug": "vercel_ai_gateway-vercel_ai_gateway-xai-grok-2-vision", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "grok-2-vision", "displayName": "grok-2-vision", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/xai/grok-2-vision", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.00001, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://vercel.com/ai-gateway/models/grok-2-vision", "https://vercel.com/docs/agent-resources/integrations-for-models/xai" ], "manual_model_modalities_note": "xAI docs list Grok-2 Vision as multimodal with visual processing." }, "benchmarks": { "gpqa_accuracy_grok2_officiallaunchpost_105": { "label": "GPQA", "category": "general_knowledge", "score": 56, "scoreText": "56.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlu_accuracy_grok2_officiallaunchpost_106": { "label": "MMLU", "category": "general_knowledge", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlupro_accuracy_grok2_officiallaunchpost_107": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "math_accuracy_grok2_officiallaunchpost_108": { "label": "MATH", "category": "math", "score": 76.1, "scoreText": "76.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "humaneval_pass1_grok2_officiallaunchpost_109": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 HumanEval is reported as pass@1." }, "mmmu_accuracy_grok2_officiallaunchpost_110": { "label": "MMMU", "category": "multimodal", "score": 66.1, "scoreText": "66.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/xai/grok-3", "slug": "vercel_ai_gateway-vercel_ai_gateway-xai-grok-3", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "grok-3", "displayName": "grok-3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/xai/grok-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4", "https://vercel.com/ai-gateway/models/grok-3" ], "manual_model_modalities_note": "The xAI Grok 4 page lists grok-3 as an alias and defines text/image input with text output." }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/xai/grok-3-fast", "slug": "vercel_ai_gateway-vercel_ai_gateway-xai-grok-3-fast", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "grok-3-fast", "displayName": "grok-3-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/xai/grok-3-fast", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000025, "supports_function_calling": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4", "https://vercel.com/ai-gateway/models/grok-3-fast" ], "manual_model_modalities_note": "The xAI Grok 4 page lists grok-3-fast as an alias and defines text/image input with text output." }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/xai/grok-3-mini", "slug": "vercel_ai_gateway-vercel_ai_gateway-xai-grok-3-mini", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "grok-3-mini", "displayName": "grok-3-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/xai/grok-3-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-7, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-mini", "https://vercel.com/ai-gateway/models/grok-3-mini" ], "manual_model_modalities_note": "The xAI Grok 3 Mini page defines text input and text output." }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/xai/grok-3-mini-fast", "slug": "vercel_ai_gateway-vercel_ai_gateway-xai-grok-3-mini-fast", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "grok-3-mini-fast", "displayName": "grok-3-mini-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/xai/grok-3-mini-fast", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000004, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-mini", "https://vercel.com/ai-gateway/models/grok-3-mini-fast" ], "manual_model_modalities_note": "The xAI Grok 3 Mini page lists grok-3-mini-fast as an alias and defines text input and text output." }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/xai/grok-4", "slug": "vercel_ai_gateway-vercel_ai_gateway-xai-grok-4", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "grok-4", "displayName": "grok-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/xai/grok-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4", "https://vercel.com/ai-gateway/models/grok-4" ], "manual_model_modalities_note": "The xAI Grok 4 page defines text/image input with text output." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/zai/glm-4.5", "slug": "vercel_ai_gateway-vercel_ai_gateway-zai-glm-4-5", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "glm-4.5", "displayName": "glm-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/zai/glm-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000022, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.z.ai/guides/llm/glm-4.5", "https://vercel.com/ai-gateway/models/glm-4.5/about" ], "manual_model_modalities_note": "Z.AI docs define GLM-4.5 as text input and text output." }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/zai/glm-4.5-air", "slug": "vercel_ai_gateway-vercel_ai_gateway-zai-glm-4-5-air", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "glm-4.5-air", "displayName": "glm-4.5-air", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000011 } }, "limits": { "contextWindow": 96000, "maxInputTokens": 128000, "maxOutputTokens": 96000, "maxTokens": 96000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/zai/glm-4.5-air", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 96000, "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 0.0000011, "supports_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.z.ai/guides/llm/glm-4.5", "https://vercel.com/ai-gateway/models/glm-4.5-air" ], "manual_model_modalities_note": "Z.AI docs define GLM-4.5-Air as text input and text output." }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "vercel_ai_gateway/vercel_ai_gateway/zai/glm-4.6", "slug": "vercel_ai_gateway-vercel_ai_gateway-zai-glm-4-6", "provider": "vercel_ai_gateway", "providerSlug": "vercel_ai_gateway", "name": "glm-4.6", "displayName": "glm-4.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.44999999999999996, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.44999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.0000018 } }, "limits": { "contextWindow": 200000, "maxInputTokens": 200000, "maxOutputTokens": 200000, "maxTokens": 200000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vercel_ai_gateway/zai/glm-4.6", "syncedAt": "2026-05-28", "sourceUrl": "https://vercel.com/ai-gateway/models/glm-4.6" }, "rawLitellm": { "litellm_provider": "vercel_ai_gateway", "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 4.5e-7, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 0.0000018, "source": "https://vercel.com/ai-gateway/models/glm-4.6", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.z.ai/guides/llm/glm-4.6", "https://vercel.com/ai-gateway/models/glm-4.6" ], "manual_model_modalities_note": "Z.AI docs define GLM-4.6 as text input and text output." }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_zaiglm46_benchmarkleaderboard_282": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_zaiglm46_benchmarkleaderboard_283": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_zaiglm46_benchmarkleaderboard_284": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_zaiglm46_benchmarkleaderboard_285": { "label": "GPQA Diamond", "category": "reasoning", "score": 78, "scoreText": "78.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_artificialanalysisintelligenceindex_score_zaiglm46_benchmarkleaderboard_310": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysiscodingindex_score_zaiglm46_benchmarkleaderboard_311": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysisagenticindex_score_zaiglm46_benchmarkleaderboard_312": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." } } }, { "id": "vertex_ai/vertex_ai/chirp", "slug": "vertex_ai-vertex_ai-chirp", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "chirp", "displayName": "chirp", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00003, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/chirp", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/text-to-speech/pricing" }, "rawLitellm": { "input_cost_per_character": 0.00003, "litellm_provider": "vertex_ai", "mode": "audio_speech", "source": "https://cloud.google.com/text-to-speech/pricing", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-5-haiku", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-5-haiku", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-5-haiku", "displayName": "claude-3-5-haiku", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "pdf_input": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-5-haiku", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000005, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_tool_choice": true }, "benchmarks": { "aidercodeeditingleaderboard_score_claude35haiku20241022_benchmarkleaderboard_68": { "label": "Aider Code Editing", "category": "coding", "score": 75.2, "scoreText": "75.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Haiku", "exactModelOrSnapshot": "claude-3-5-haiku-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-5-haiku@20241022", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-5-haiku-20241022", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-5-haiku@20241022", "displayName": "claude-3-5-haiku@20241022", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "pdf_input": true, "tool_choice": true } }, "modalities": { "supported": [ "code", "image", "text" ], "input": [ "code", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-5-haiku@20241022", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000005, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-3-5", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vertex Anthropic exact snapshot ids from official docs" }, "benchmarks": { "aidercodeeditingleaderboard_score_claude35haiku20241022_benchmarkleaderboard_68": { "label": "Aider Code Editing", "category": "coding", "score": 75.2, "scoreText": "75.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Haiku", "exactModelOrSnapshot": "claude-3-5-haiku-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-haiku-4-5", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-haiku-4-5", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-haiku-4-5", "displayName": "claude-haiku-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": 1.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000125, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "native_streaming": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-haiku-4-5", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000125, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_native_streaming": true, "supports_vision": true }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-haiku-4-5@20251001", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-haiku-4-5-20251001", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-haiku-4-5@20251001", "displayName": "claude-haiku-4-5@20251001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": 1.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000125, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "native_streaming": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-haiku-4-5@20251001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000125, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000005, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_native_streaming": true, "supports_vision": true }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-5-sonnet", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-5-sonnet", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-5-sonnet", "displayName": "claude-3-5-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-5-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-5-sonnet@20240620", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-5-sonnet-20240620", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-5-sonnet@20240620", "displayName": "claude-3-5-sonnet@20240620", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "pdf_input": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "code", "image", "text" ], "input": [ "code", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-5-sonnet@20240620", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/deprecations/partner-models", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vertex Anthropic exact snapshot ids from official docs" }, "benchmarks": { "swebenchverified_score_claude35sonnet_officiallaunchpost_63": { "label": "SWE-bench Verified", "category": "coding", "score": 49, "scoreText": "49%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/swe-bench-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "Claude 3.5 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified release post." }, "aidercodeeditingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_64": { "label": "Aider Code Editing", "category": "coding", "score": 84.2, "scoreText": "84.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Old code-editing leaderboard row; diff edit format." }, "aiderpolyglotcodingleaderboard_score_claude35sonnet20241022_benchmarkleaderboard_65": { "label": "Aider Polyglot", "category": "coding", "score": 45.3, "scoreText": "45.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.5 Sonnet", "exactModelOrSnapshot": "claude-3-5-sonnet-20241022", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-7-sonnet@20250219", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-7-sonnet-20250219", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-7-sonnet@20250219", "displayName": "claude-3-7-sonnet@20250219", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 200000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "code", "image", "text" ], "input": [ "code", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-05-11" }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-7-sonnet@20250219", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "deprecation_date": "2026-05-11", "input_cost_per_token": 0.000003, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/deprecations/partner-models", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vertex Anthropic exact snapshot ids from official docs" }, "benchmarks": { "swebenchverified_score_claude37sonnet_officiallaunchpost_61": { "label": "SWE-bench Verified", "category": "coding", "score": 70.3, "scoreText": "70.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Scaffolded SWE-bench result on the 489-task internal subset." }, "swebenchverified_score_claude37sonnet_officiallaunchpost_62": { "label": "SWE-bench Verified", "category": "coding", "score": 63.7, "scoreText": "63.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-3-7-sonnet", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "Claude 3.7 Sonnet", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Same SWE-bench subset, without the scaffold." }, "aiderpolyglotcodingleaderboard_score_claude37sonnet20250219nothinking_benchmarkleaderboard_67": { "label": "Aider Polyglot", "category": "coding", "score": 60.4, "scoreText": "60.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3.7 Sonnet", "exactModelOrSnapshot": "claude-3-7-sonnet-20250219 (no thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-haiku", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-haiku", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-haiku", "displayName": "claude-3-haiku", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-haiku", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-haiku@20240307", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-haiku-20240307", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-haiku@20240307", "displayName": "claude-3-haiku@20240307", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "code", "image", "text" ], "input": [ "code", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-haiku@20240307", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00000125, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-3", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vertex Anthropic exact snapshot ids from official docs" } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-opus", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-opus", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-opus", "displayName": "claude-3-opus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-opus", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000075, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "aiderrefactoringleaderboard_score_claude3opus20240229_benchmarkleaderboard_69": { "label": "Aider Refactoring", "category": "coding", "score": 72.3, "scoreText": "72.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/refactor.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3 Opus", "exactModelOrSnapshot": "claude-3-opus-20240229", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Refactoring leaderboard row; diff edit format." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-opus@20240229", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-opus-20240229", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-opus@20240229", "displayName": "claude-3-opus@20240229", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "code", "image", "text" ], "input": [ "code", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-opus@20240229", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000015, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000075, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/deprecations/partner-models", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vertex Anthropic exact snapshot ids from official docs" }, "benchmarks": { "aiderrefactoringleaderboard_score_claude3opus20240229_benchmarkleaderboard_69": { "label": "Aider Refactoring", "category": "coding", "score": 72.3, "scoreText": "72.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/refactor.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 3 Opus", "exactModelOrSnapshot": "claude-3-opus-20240229", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Refactoring leaderboard row; diff edit format." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-sonnet", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-sonnet", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-sonnet", "displayName": "claude-3-sonnet", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-sonnet", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-3-sonnet@20240229", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-3-sonnet-20240229", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-3-sonnet@20240229", "displayName": "claude-3-sonnet@20240229", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 200000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-3-sonnet@20240229", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-opus-4", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-opus-4", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-opus-4", "displayName": "claude-opus-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-opus-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-1", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-opus-4-1", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-opus-4-1", "displayName": "claude-opus-4-1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 7.5, "batchOutputUsdPer1MTokens": 37.5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "input_cost_per_token_batches": 0.0000075, "output_cost_per_token": 0.000075, "output_cost_per_token_batches": 0.0000375 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-opus-4-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "input_cost_per_token_batches": 0.0000075, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "output_cost_per_token_batches": 0.0000375, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-1@20250805", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-opus-4-1-20250805", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-opus-4-1@20250805", "displayName": "claude-opus-4-1@20250805", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 7.5, "batchOutputUsdPer1MTokens": 37.5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "input_cost_per_token_batches": 0.0000075, "output_cost_per_token": 0.000075, "output_cost_per_token_batches": 0.0000375 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "code", "image", "text" ], "input": [ "code", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-opus-4-1@20250805", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "input_cost_per_token_batches": 0.0000075, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "output_cost_per_token_batches": 0.0000375, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/opus-4-1", "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/opus-4", "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/sonnet-4", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vertex Anthropic exact snapshot ids from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-5", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-opus-4-5", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-opus-4-5", "displayName": "claude-opus-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "minimal_reasoning_effort": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-opus-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-5@20251101", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-opus-4-5-20251101", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-opus-4-5@20251101", "displayName": "claude-opus-4-5@20251101", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "minimal_reasoning_effort": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_streaming": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-opus-4-5@20251101", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "supports_native_streaming": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claude45opusmediumeffort_benchmarkleaderboard_41": { "label": "LiveBench", "category": "other", "score": 59.1, "scoreText": "59.10", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude 4.5 Opus Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Medium Effort variant." }, "swebenchverified_score_claudeopus45_officialdocs_42": { "label": "SWE-bench Verified", "category": "coding", "score": 80.9, "scoreText": "80.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "terminalbench20_score_claudeopus45_officialdocs_44": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 59.8, "scoreText": "59.8%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "benchretail_score_claudeopus45_officialdocs_46": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 88.9, "scoreText": "88.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "gpqadiamond_score_claudeopus45_officialdocs_48": { "label": "GPQA Diamond", "category": "science", "score": 87, "scoreText": "87.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Opus 4.5 column." }, "swebenchverified_resolved_claude45opushighreasoning_benchmarkleaderboard_214": { "label": "SWE-bench Verified", "category": "coding", "score": 76.8, "scoreText": "76.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "livebench_livebenchscore_claude45opusthinkinghigheffort_benchmarkleaderboard_232": { "label": "LiveBench", "category": "general_knowledge", "score": 75.96, "scoreText": "75.96", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Opus", "exactModelOrSnapshot": "Claude 4.5 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus4520251101thinking32k_benchmarkleaderboard_243": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1484, "scoreText": "1484±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "claude-opus-4-5-20251101-thinking-32k", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row for the thinking 32k variant." }, "mmlupro_accuracy_claudeopus45reasoning_benchmarkleaderboard_250": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.5", "exactModelOrSnapshot": "Claude Opus 4.5 (Reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the reasoning variant." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-6", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-opus-4-6", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-opus-4-6", "displayName": "claude-opus-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "output_config": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-opus-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-6@default", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-opus-4-6-default", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-opus-4-6@default", "displayName": "claude-opus-4-6@default", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "output_config": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-opus-4-6@default", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46opusthinkinghigheffort_benchmarkleaderboard_231": { "label": "LiveBench", "category": "general_knowledge", "score": 76.33, "scoreText": "76.33", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Opus", "exactModelOrSnapshot": "Claude 4.6 Opus Thinking High Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46thinking_benchmarkleaderboard_235": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1516, "scoreText": "1516±6", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus46_benchmarkleaderboard_237": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1508, "scoreText": "1508±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.6", "exactModelOrSnapshot": "claude-opus-4-6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-7", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-opus-4-7", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-opus-4-7", "displayName": "claude-opus-4-7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": true }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-opus-4-7", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-opus-4-7@default", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-opus-4-7-default", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-opus-4-7@default", "displayName": "claude-opus-4-7@default", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 0.5, "cacheWriteUsdPer1MTokens": 6.25, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 1000000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": true }, "raw": { "assistant_prefill": false, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "xhigh_reasoning_effort": true, "max_reasoning_effort": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-opus-4-7@default", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000625, "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude47opusthinkingxhigheffort_benchmarkleaderboard_230": { "label": "LiveBench", "category": "general_knowledge", "score": 76.91, "scoreText": "76.91", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.7 Opus", "exactModelOrSnapshot": "Claude 4.7 Opus Thinking xHigh Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47thinking_benchmarkleaderboard_236": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1509, "scoreText": "1509±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7-thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "LMArena text arena row; normalized family from a thinking variant." }, "lmarenatextarenaenglish_arenaelo_claudeopus47_benchmarkleaderboard_238": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1501, "scoreText": "1501±7", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4.7", "exactModelOrSnapshot": "claude-opus-4-7", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row without an explicit route qualifier." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4-5", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-sonnet-4-5", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-sonnet-4-5", "displayName": "claude-sonnet-4-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.5, "batchOutputUsdPer1MTokens": 7.5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "output_cost_per_token": 0.000015, "output_cost_per_token_batches": 0.0000075 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-sonnet-4-5", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_batches": 0.0000075, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4-6", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-sonnet-4-6", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-sonnet-4-6", "displayName": "claude-sonnet-4-6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "output_config": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-sonnet-4-6", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_output_config": true, "supports_minimal_reasoning_effort": true }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4-5@20250929", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-sonnet-4-5-20250929", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-sonnet-4-5@20250929", "displayName": "claude-sonnet-4-5@20250929", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1.5, "batchOutputUsdPer1MTokens": 7.5, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "output_cost_per_token": 0.000015, "output_cost_per_token_batches": 0.0000075 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_streaming": true } }, "modalities": { "supported": [ "code", "documents", "image", "text" ], "input": [ "code", "documents", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-sonnet-4-5@20250929", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_batches": 0.0000075, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_streaming": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/sonnet-4-5", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vertex Anthropic exact snapshot ids from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_score_claudesonnet45thinking_benchmarkleaderboard_40": { "label": "LiveBench", "category": "other", "score": 68.19, "scoreText": "68.19", "metric": "score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5 Thinking", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Overall LiveBench score row for the Thinking variant." }, "swebenchverified_score_claudesonnet45_officialdocs_43": { "label": "SWE-bench Verified", "category": "coding", "score": 77.2, "scoreText": "77.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "terminalbench20_score_claudesonnet45_officialdocs_45": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 51, "scoreText": "51.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "benchretail_score_claudesonnet45_officialdocs_47": { "label": "τ²-bench (Retail)", "category": "agentic", "score": 86.2, "scoreText": "86.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "gpqadiamond_score_claudesonnet45_officialdocs_49": { "label": "GPQA Diamond", "category": "science", "score": 83.4, "scoreText": "83.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www-cdn.anthropic.com/bbd8ef16d70b7a1665f14f306ee88b53f686aa75.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "Claude Sonnet 4.5", "modelDeveloper": "Anthropic", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "System-card comparison table; Sonnet 4.5 column." }, "swebenchverified_score_claudesonnet45_officiallaunchpost_51": { "label": "SWE-bench Verified", "category": "coding", "score": 82, "scoreText": "82.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-sonnet-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "High-compute SWE-bench result from the launch post." }, "aiderpolyglotcodingleaderboard_score_claudesonnet42025051432kthinking_benchmarkleaderboard_66": { "label": "Aider Polyglot", "category": "coding", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.5", "exactModelOrSnapshot": "claude-sonnet-4-20250514 (32k thinking)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Polyglot leaderboard row; diff edit format." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-opus-4@20250514", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-opus-4-20250514", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-opus-4@20250514", "displayName": "claude-opus-4@20250514", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15, "outputUsdPer1MTokens": 75, "cachedInputUsdPer1MTokens": 1.5, "cacheWriteUsdPer1MTokens": 18.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 200000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "code", "image", "text" ], "input": [ "code", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-opus-4@20250514", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00001875, "cache_read_input_token_cost": 0.0000015, "input_cost_per_token": 0.000015, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/opus-4", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vertex Anthropic exact snapshot ids from official docs" }, "benchmarks": { "swebenchverified_score_claudeopus4_officiallaunchpost_52": { "label": "SWE-bench Verified", "category": "coding", "score": 72.5, "scoreText": "72.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "terminalbench_score_claudeopus4_officiallaunchpost_54": { "label": "Terminal-Bench", "category": "agentic", "score": 43.2, "scoreText": "43.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudeopus4_officiallaunchpost_55": { "label": "GPQA Diamond", "category": "science", "score": 74.9, "scoreText": "74.9%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudeopus4_officiallaunchpost_57": { "label": "MMMLU", "category": "general_knowledge", "score": 87.4, "scoreText": "87.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudeopus4_officiallaunchpost_59": { "label": "MMMU", "category": "multimodal", "score": 73.7, "scoreText": "73.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Opus 4", "exactModelOrSnapshot": "Claude Opus 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-sonnet-4", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-sonnet-4", "displayName": "claude-sonnet-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-sonnet-4", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4@20250514", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-sonnet-4-20250514", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-sonnet-4@20250514", "displayName": "claude-sonnet-4@20250514", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 6, "above200kOutputUsdPer1MTokens": 22.5, "above200kCachedInputUsdPer1MTokens": 0.6, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [ "code", "image", "text" ], "input": [ "code", "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-sonnet-4@20250514", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 159, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/sonnet-4", "https://docs.anthropic.com/en/docs/about-claude/models/overview" ], "manual_model_modalities_note": "Vertex Anthropic exact snapshot ids from official docs" }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." } } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistralai/codestral-2@001", "slug": "vertex_ai-mistral_models-vertex_ai-mistralai-codestral-2-001", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "codestral-2@001", "displayName": "codestral-2@001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistralai/codestral-2@001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-7, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "vertex_ai-mistral_models/vertex_ai/codestral-2", "slug": "vertex_ai-mistral_models-vertex_ai-codestral-2", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "codestral-2", "displayName": "codestral-2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/codestral-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-7, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "vertex_ai-mistral_models/vertex_ai/codestral-2@001", "slug": "vertex_ai-mistral_models-vertex_ai-codestral-2-001", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "codestral-2@001", "displayName": "codestral-2@001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/codestral-2@001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-7, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistralai/codestral-2", "slug": "vertex_ai-mistral_models-vertex_ai-mistralai-codestral-2", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "codestral-2", "displayName": "codestral-2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistralai/codestral-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-7, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "vertex_ai-mistral_models/vertex_ai/codestral-2501", "slug": "vertex_ai-mistral_models-vertex_ai-codestral-2501", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "codestral-2501", "displayName": "codestral-2501", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/codestral-2501", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "vertex_ai-mistral_models/vertex_ai/codestral@2405", "slug": "vertex_ai-mistral_models-vertex_ai-codestral-2405", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "codestral@2405", "displayName": "codestral@2405", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/codestral@2405", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "vertex_ai-mistral_models/vertex_ai/codestral@latest", "slug": "vertex_ai-mistral_models-vertex_ai-codestral-latest", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "codestral@latest", "displayName": "codestral@latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/codestral@latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_codestral2501overviewtable_humaneval_codestral2405_officiallaunchpost_149": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 81.1, "scoreText": "81.1%", "metric": "HumanEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_mbpp_codestral2405_officiallaunchpost_150": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 78.2, "scoreText": "78.2%", "metric": "MBPP", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_cruxeval_codestral2405_officiallaunchpost_151": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 51.3, "scoreText": "51.3%", "metric": "CruxEval", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_livecodebench_codestral2405_officiallaunchpost_152": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 31.5, "scoreText": "31.5%", "metric": "LiveCodeBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_repobench_codestral2405_officiallaunchpost_153": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 34, "scoreText": "34.0%", "metric": "RepoBench", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_spider_codestral2405_officiallaunchpost_154": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 63.5, "scoreText": "63.5%", "metric": "Spider", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_canitedit_codestral2405_officiallaunchpost_155": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 50.5, "scoreText": "50.5%", "metric": "CanItEdit", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalaverage_codestral2405_officiallaunchpost_156": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 65.6, "scoreText": "65.6%", "metric": "HumanEval (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_codestral2501overviewtable_humanevalfimaverage_codestral2405_officiallaunchpost_157": { "label": "Codestral 25.01 overview table", "category": "coding", "score": 82.1, "scoreText": "82.1%", "metric": "HumanEvalFIM (average)", "higherIsBetter": true, "source_url": "https://mistral.ai/fr/news/codestral-2501", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral-2405", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official Codestral 25.01 benchmark table for the 2405 snapshot." }, "local_aiderpolyglot_percentcorrect_codestral2501_benchmarkleaderboard_248": { "label": "Aider Polyglot", "category": "agentic", "score": 11.1, "scoreText": "11.1%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Codestral", "exactModelOrSnapshot": "Codestral 25.01", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the Codestral family's 25.01 snapshot." } } }, { "id": "vertex_ai-deepseek_models/vertex_ai/deepseek-ai/deepseek-v3.1-maas", "slug": "vertex_ai-deepseek_models-vertex_ai-deepseek-ai-deepseek-v3-1-maas", "provider": "vertex_ai-deepseek_models", "providerSlug": "vertex_ai-deepseek_models", "name": "deepseek-v3.1-maas", "displayName": "deepseek-v3.1-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.35, "outputUsdPer1MTokens": 5.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 163840, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/deepseek-ai/deepseek-v3.1-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 0.00000135, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000054, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "us-central1" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "vertex_ai-deepseek_models/vertex_ai/deepseek-ai/deepseek-v3.2-maas", "slug": "vertex_ai-deepseek_models-vertex_ai-deepseek-ai-deepseek-v3-2-maas", "provider": "vertex_ai-deepseek_models", "providerSlug": "vertex_ai-deepseek_models", "name": "deepseek-v3.2-maas", "displayName": "deepseek-v3.2-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.56, "outputUsdPer1MTokens": 1.68, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.56, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.28, "batchOutputUsdPer1MTokens": 0.84, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.6e-7, "input_cost_per_token_batches": 2.8e-7, "output_cost_per_token": 0.00000168, "output_cost_per_token_batches": 8.4e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 163840, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/deepseek-ai/deepseek-v3.2-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 5.6e-7, "input_cost_per_token_batches": 2.8e-7, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.00000168, "output_cost_per_token_batches": 8.4e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "global" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "vertex_ai-deepseek_models/vertex_ai/deepseek-ai/deepseek-r1-0528-maas", "slug": "vertex_ai-deepseek_models-vertex_ai-deepseek-ai-deepseek-r1-0528-maas", "provider": "vertex_ai-deepseek_models", "providerSlug": "vertex_ai-deepseek_models", "name": "deepseek-r1-0528-maas", "displayName": "deepseek-r1-0528-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.35, "outputUsdPer1MTokens": 5.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 65336, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/deepseek-ai/deepseek-r1-0528-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 0.00000135, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000054, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "us-central1" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "vertex_ai-language-models/vertex_ai/gemini-2.5-flash-image", "slug": "vertex_ai-language-models-vertex_ai-gemini-2-5-flash-image", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-2.5-flash-image", "displayName": "gemini-2.5-flash-image", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 39000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_image": 0.039, "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "tpm": 8000000 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 100000, "tpm": 8000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": false } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "image", "text" ], "output": [ "image", "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-2.5-flash-image", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image" }, "rawLitellm": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "max_pdf_size_mb": 30, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": false, "tpm": 8000000, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Images and text Output Images and text" } }, { "id": "vertex_ai-language-models/vertex_ai/gemini-3-pro-image-preview", "slug": "vertex_ai-language-models-vertex_ai-gemini-3-pro-image-preview", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3-pro-image-preview", "displayName": "gemini-3-pro-image-preview", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 1100, "imageOutputUsdPer1MUnits": 134000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 65536, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "image", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-3-pro-image-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" }, "rawLitellm": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Image and Text Output Image and Text" }, "benchmarks": { "humanityslastexam_accuracy_gemini3prothinkinghigh_officialdocs_96": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 37.5, "scoreText": "37.5% (no tools)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "arcagi2_accuracy_gemini3prothinkinghigh_officialdocs_97": { "label": "ARC-AGI-2", "category": "reasoning", "score": 31.1, "scoreText": "31.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "gpqadiamond_accuracy_gemini3prothinkinghigh_officialdocs_98": { "label": "GPQA Diamond", "category": "science", "score": 91.9, "scoreText": "91.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "terminalbench20_accuracy_gemini3prothinkinghigh_officialdocs_99": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 56.9, "scoreText": "56.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_accuracy_gemini3prothinkinghigh_officialdocs_100": { "label": "SWE-bench Verified", "category": "agentic", "score": 76.2, "scoreText": "76.2% (single attempt)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "livecodebenchpro_elo_gemini3prothinkinghigh_officialdocs_101": { "label": "LiveCodeBench Pro", "category": "coding", "score": 2439, "scoreText": "2439 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mmmupro_accuracy_gemini3prothinkinghigh_officialdocs_102": { "label": "MMMU-Pro", "category": "multimodal", "score": 81, "scoreText": "81.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_103": { "label": "MRCR v2", "category": "long_context", "score": 77, "scoreText": "77.0% (128k average)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "mrcrv2_accuracy_gemini3prothinkinghigh_officialdocs_104": { "label": "MRCR v2", "category": "long_context", "score": 26.3, "scoreText": "26.3% (1M pointwise)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://deepmind.google/models/gemini/pro/", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro Thinking (High)", "modelDeveloper": "Google DeepMind", "sourceType": "official_docs", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page; selected the Gemini 3 Pro Thinking (High) column from the benchmark table." }, "swebenchverified_resolved_gemini3pro_benchmarkleaderboard_217": { "label": "SWE-bench Verified", "category": "coding", "score": 69.6, "scoreText": "69.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "Gemini 3 Pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row shown without a route qualifier." }, "lmarenatextarenaenglish_arenaelo_gemini3pro_benchmarkleaderboard_241": { "label": "LMArena Text Arena (English)", "category": "preference", "score": 1489, "scoreText": "1489±5", "metric": "Arena Elo", "higherIsBetter": true, "source_url": "https://arena.ai/leaderboard/text/english", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro", "exactModelOrSnapshot": "gemini-3-pro", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "LMArena text arena row shown without a route qualifier." }, "mmlupro_accuracy_gemini3propreviewhigh_benchmarkleaderboard_248": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.8, "scoreText": "89.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (high)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard top row summarized on the page." }, "mmlupro_accuracy_gemini3propreviewlow_benchmarkleaderboard_249": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 89.5, "scoreText": "89.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://artificialanalysis.ai/evaluations/mmlu-pro", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 3 Pro Preview", "exactModelOrSnapshot": "Gemini 3 Pro Preview (low)", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Artificial Analysis MMLU-Pro leaderboard row for the low variant." } } }, { "id": "vertex_ai-language-models/vertex_ai/gemini-3.1-flash-image-preview", "slug": "vertex_ai-language-models-vertex_ai-gemini-3-1-flash-image-preview", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3.1-flash-image-preview", "displayName": "gemini-3.1-flash-image-preview", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 560, "imageOutputUsdPer1MUnits": 67200, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-7, "output_cost_per_image": 0.0672, "output_cost_per_image_token": 0.00006, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 65536, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "pdf", "text" ], "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-3.1-flash-image-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "rawLitellm": { "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-7, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 0.00006, "output_cost_per_token": 0.000003, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text and Image / PDF Output Image and Text" } }, { "id": "vertex_ai-language-models/vertex_ai/gemini-3.1-flash-lite-preview", "slug": "vertex_ai-language-models-vertex_ai-gemini-3-1-flash-lite-preview", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3.1-flash-lite-preview", "displayName": "gemini-3.1-flash-lite-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 1.5, "audioInputUsdPer1MTokens": 0.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": false, "code_execution": true, "file_search": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-3.1-flash-lite-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_code_execution": true, "supports_file_search": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text" } }, { "id": "vertex_ai-language-models/vertex_ai/gemini-3.1-flash-lite", "slug": "vertex_ai-language-models-vertex_ai-gemini-3-1-flash-lite", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "gemini-3.1-flash-lite", "displayName": "gemini-3.1-flash-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.024999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 1.5, "audioInputUsdPer1MTokens": 0.5, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 0.125, "batchOutputUsdPer1MTokens": 0.75, "batchCachedInputUsdPer1MTokens": 0.012499999999999999, "priorityInputUsdPer1MTokens": 0.44999999999999996, "priorityOutputUsdPer1MTokens": 2.7, "priorityCachedInputUsdPer1MTokens": 0.045, "flexInputUsdPer1MTokens": 0.125, "flexOutputUsdPer1MTokens": 0.75, "flexCachedInputUsdPer1MTokens": 0.012499999999999999, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "web_search_billing_unit": "per_query" } }, "limits": { "contextWindow": 65536, "maxInputTokens": 1048576, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": true, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": true, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": false, "code_execution": true, "file_search": true, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "video_input": true, "vision": true, "web_search": true, "native_streaming": true, "service_tier": true } }, "modalities": { "supported": [ "audio", "image", "pdf", "text", "video" ], "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/gemini-3.1-flash-lite", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "rawLitellm": { "cache_read_input_token_cost": 2.5e-8, "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token": 2.5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_code_execution": true, "supports_file_search": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "supports_service_tier": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, Image, Video, Audio, and PDF Output Text" } }, { "id": "vertex_ai-language-models/vertex_ai/deep-research-pro-preview-12-2025", "slug": "vertex_ai-language-models-vertex_ai-deep-research-pro-preview-12-2025", "provider": "vertex_ai-language-models", "providerSlug": "vertex_ai-language-models", "name": "deep-research-pro-preview-12-2025", "displayName": "deep-research-pro-preview-12-2025", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 1100, "imageOutputUsdPer1MUnits": 134000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": 1, "batchOutputUsdPer1MTokens": 6, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 65536, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/deep-research-pro-preview-12-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" }, "rawLitellm": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" } }, { "id": "vertex_ai-image-models/vertex_ai/imagegeneration@006", "slug": "vertex_ai-image-models-vertex_ai-imagegeneration-006", "provider": "vertex_ai-image-models", "providerSlug": "vertex_ai-image-models", "name": "imagegeneration@006", "displayName": "imagegeneration@006", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 20000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.02 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/imagegeneration@006", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "id": "vertex_ai-image-models/vertex_ai/imagen-3.0-fast-generate-001", "slug": "vertex_ai-image-models-vertex_ai-imagen-3-0-fast-generate-001", "provider": "vertex_ai-image-models", "providerSlug": "vertex_ai-image-models", "name": "imagen-3.0-fast-generate-001", "displayName": "imagen-3.0-fast-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 20000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.02 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/imagen-3.0-fast-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "id": "vertex_ai-image-models/vertex_ai/imagen-3.0-generate-001", "slug": "vertex_ai-image-models-vertex_ai-imagen-3-0-generate-001", "provider": "vertex_ai-image-models", "providerSlug": "vertex_ai-image-models", "name": "imagen-3.0-generate-001", "displayName": "imagen-3.0-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/imagen-3.0-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "id": "vertex_ai-image-models/vertex_ai/imagen-3.0-generate-002", "slug": "vertex_ai-image-models-vertex_ai-imagen-3-0-generate-002", "provider": "vertex_ai-image-models", "providerSlug": "vertex_ai-image-models", "name": "imagen-3.0-generate-002", "displayName": "imagen-3.0-generate-002", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": "2025-11-10" }, "source": { "type": "litellm", "litellmKey": "vertex_ai/imagen-3.0-generate-002", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "deprecation_date": "2025-11-10", "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "id": "vertex_ai-image-models/vertex_ai/imagen-3.0-capability-001", "slug": "vertex_ai-image-models-vertex_ai-imagen-3-0-capability-001", "provider": "vertex_ai-image-models", "providerSlug": "vertex_ai-image-models", "name": "imagen-3.0-capability-001", "displayName": "imagen-3.0-capability-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/imagen-3.0-capability-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects" }, "rawLitellm": { "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects" } }, { "id": "vertex_ai-image-models/vertex_ai/imagen-4.0-fast-generate-001", "slug": "vertex_ai-image-models-vertex_ai-imagen-4-0-fast-generate-001", "provider": "vertex_ai-image-models", "providerSlug": "vertex_ai-image-models", "name": "imagen-4.0-fast-generate-001", "displayName": "imagen-4.0-fast-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 20000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.02 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/imagen-4.0-fast-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "id": "vertex_ai-image-models/vertex_ai/imagen-4.0-generate-001", "slug": "vertex_ai-image-models-vertex_ai-imagen-4-0-generate-001", "provider": "vertex_ai-image-models", "providerSlug": "vertex_ai-image-models", "name": "imagen-4.0-generate-001", "displayName": "imagen-4.0-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 40000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.04 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/imagen-4.0-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "id": "vertex_ai-image-models/vertex_ai/imagen-4.0-ultra-generate-001", "slug": "vertex_ai-image-models-vertex_ai-imagen-4-0-ultra-generate-001", "provider": "vertex_ai-image-models", "providerSlug": "vertex_ai-image-models", "name": "imagen-4.0-ultra-generate-001", "displayName": "imagen-4.0-ultra-generate-001", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 60000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_image": 0.06 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/imagen-4.0-ultra-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" } }, { "id": "vertex_ai-ai21_models/vertex_ai/jamba-1.5", "slug": "vertex_ai-ai21_models-vertex_ai-jamba-1-5", "provider": "vertex_ai-ai21_models", "providerSlug": "vertex_ai-ai21_models", "name": "jamba-1.5", "displayName": "jamba-1.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/jamba-1.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-7, "supports_tool_choice": true } }, { "id": "vertex_ai-ai21_models/vertex_ai/jamba-1.5-large", "slug": "vertex_ai-ai21_models-vertex_ai-jamba-1-5-large", "provider": "vertex_ai-ai21_models", "providerSlug": "vertex_ai-ai21_models", "name": "jamba-1.5-large", "displayName": "jamba-1.5-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/jamba-1.5-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000008, "supports_tool_choice": true } }, { "id": "vertex_ai-ai21_models/vertex_ai/jamba-1.5-large@001", "slug": "vertex_ai-ai21_models-vertex_ai-jamba-1-5-large-001", "provider": "vertex_ai-ai21_models", "providerSlug": "vertex_ai-ai21_models", "name": "jamba-1.5-large@001", "displayName": "jamba-1.5-large@001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 8, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/jamba-1.5-large@001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000008, "supports_tool_choice": true } }, { "id": "vertex_ai-ai21_models/vertex_ai/jamba-1.5-mini", "slug": "vertex_ai-ai21_models-vertex_ai-jamba-1-5-mini", "provider": "vertex_ai-ai21_models", "providerSlug": "vertex_ai-ai21_models", "name": "jamba-1.5-mini", "displayName": "jamba-1.5-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/jamba-1.5-mini", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-7, "supports_tool_choice": true } }, { "id": "vertex_ai-ai21_models/vertex_ai/jamba-1.5-mini@001", "slug": "vertex_ai-ai21_models-vertex_ai-jamba-1-5-mini-001", "provider": "vertex_ai-ai21_models", "providerSlug": "vertex_ai-ai21_models", "name": "jamba-1.5-mini@001", "displayName": "jamba-1.5-mini@001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/jamba-1.5-mini@001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-7, "supports_tool_choice": true } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama-3.1-405b-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama-3-1-405b-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama-3.1-405b-instruct-maas", "displayName": "llama-3.1-405b-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 16, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000016 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama-3.1-405b-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.000016, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama-3.1-70b-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama-3-1-70b-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama-3.1-70b-instruct-maas", "displayName": "llama-3.1-70b-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama-3.1-70b-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama-3.1-8b-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama-3-1-8b-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama-3.1-8b-instruct-maas", "displayName": "llama-3.1-8b-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama-3.1-8b-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." }, "mode": "chat", "output_cost_per_token": 0, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama-3.2-90b-vision-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama-3-2-90b-vision-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama-3.2-90b-vision-instruct-maas", "displayName": "llama-3.2-90b-vision-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 128000, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." }, "mode": "chat", "output_cost_per_token": 0, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama-4-maverick-17b-128e-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama-4-maverick-17b-128e-instruct-maas", "displayName": "llama-4-maverick-17b-128e-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 1.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.00000115 } }, "limits": { "contextWindow": 1000000, "maxInputTokens": 1000000, "maxOutputTokens": 1000000, "maxTokens": 1000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "code" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 3.5e-7, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.00000115, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama-4-maverick-17b-16e-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama-4-maverick-17b-16e-instruct-maas", "displayName": "llama-4-maverick-17b-16e-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 1.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.00000115 } }, "limits": { "contextWindow": 1000000, "maxInputTokens": 1000000, "maxOutputTokens": 1000000, "maxTokens": 1000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "code" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 3.5e-7, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.00000115, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama-4-scout-17b-128e-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama-4-scout-17b-128e-instruct-maas", "displayName": "llama-4-scout-17b-128e-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7e-7 } }, "limits": { "contextWindow": 10000000, "maxInputTokens": 10000000, "maxOutputTokens": 10000000, "maxTokens": 10000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "code" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama-4-scout-17b-16e-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama-4-scout-17b-16e-instruct-maas", "displayName": "llama-4-scout-17b-16e-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7e-7 } }, "limits": { "contextWindow": 10000000, "maxInputTokens": 10000000, "maxOutputTokens": 10000000, "maxTokens": 10000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "code" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama3-405b-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama3-405b-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama3-405b-instruct-maas", "displayName": "llama3-405b-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama3-405b-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama3-70b-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama3-70b-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama3-70b-instruct-maas", "displayName": "llama3-70b-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama3-70b-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true } }, { "id": "vertex_ai-llama_models/vertex_ai/meta/llama3-8b-instruct-maas", "slug": "vertex_ai-llama_models-vertex_ai-meta-llama3-8b-instruct-maas", "provider": "vertex_ai-llama_models", "providerSlug": "vertex_ai-llama_models", "name": "llama3-8b-instruct-maas", "displayName": "llama3-8b-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/meta/llama3-8b-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true } }, { "id": "vertex_ai-minimax_models/vertex_ai/minimaxai/minimax-m2-maas", "slug": "vertex_ai-minimax_models-vertex_ai-minimaxai-minimax-m2-maas", "provider": "vertex_ai-minimax_models", "providerSlug": "vertex_ai-minimax_models", "name": "minimax-m2-maas", "displayName": "minimax-m2-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 196608, "maxInputTokens": 196608, "maxOutputTokens": 196608, "maxTokens": 196608, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/minimaxai/minimax-m2-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-minimax_models", "max_input_tokens": 196608, "max_output_tokens": 196608, "max_tokens": 196608, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "vertex_ai-moonshot_models/vertex_ai/moonshotai/kimi-k2-thinking-maas", "slug": "vertex_ai-moonshot_models-vertex_ai-moonshotai-kimi-k2-thinking-maas", "provider": "vertex_ai-moonshot_models", "providerSlug": "vertex_ai-moonshot_models", "name": "kimi-k2-thinking-maas", "displayName": "kimi-k2-thinking-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/moonshotai/kimi-k2-thinking-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "vertex_ai-moonshot_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true } }, { "id": "vertex_ai-zai_models/vertex_ai/zai-org/glm-4.7-maas", "slug": "vertex_ai-zai_models-vertex_ai-zai-org-glm-4-7-maas", "provider": "vertex_ai-zai_models", "providerSlug": "vertex_ai-zai_models", "name": "glm-4.7-maas", "displayName": "glm-4.7-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/zai-org/glm-4.7-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000022, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "vertex_ai-zai_models/vertex_ai/zai-org/glm-5-maas", "slug": "vertex_ai-zai_models-vertex_ai-zai-org-glm-5-maas", "provider": "vertex_ai-zai_models", "providerSlug": "vertex_ai-zai_models", "name": "glm-5-maas", "displayName": "glm-5-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3.1999999999999997, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/zai-org/glm-5-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models" }, "rawLitellm": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000032, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "benchmarks": { "hle_score_glm5_officialmodelcard_165": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 30.5, "scoreText": "30.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "gpqadiamond_score_glm5_officialmodelcard_166": { "label": "GPQA Diamond", "category": "reasoning", "score": 86, "scoreText": "86.0", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchverified_score_glm5_officialmodelcard_167": { "label": "SWE-bench Verified", "category": "coding", "score": 77.8, "scoreText": "77.8", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistral-medium-3", "slug": "vertex_ai-mistral_models-vertex_ai-mistral-medium-3", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-medium-3", "displayName": "mistral-medium-3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 128000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-medium-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistral-medium-3@001", "slug": "vertex_ai-mistral_models-vertex_ai-mistral-medium-3-001", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-medium-3@001", "displayName": "mistral-medium-3@001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 128000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-medium-3@001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistralai/mistral-medium-3", "slug": "vertex_ai-mistral_models-vertex_ai-mistralai-mistral-medium-3", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-medium-3", "displayName": "mistral-medium-3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 128000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistralai/mistral-medium-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistralai/mistral-medium-3@001", "slug": "vertex_ai-mistral_models-vertex_ai-mistralai-mistral-medium-3-001", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-medium-3@001", "displayName": "mistral-medium-3@001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 128000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistralai/mistral-medium-3@001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 4e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistral-large-2411", "slug": "vertex_ai-mistral_models-vertex_ai-mistral-large-2411", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-large-2411", "displayName": "mistral-large-2411", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 128000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-large-2411", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000006, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistral-large@2407", "slug": "vertex_ai-mistral_models-vertex_ai-mistral-large-2407", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-large@2407", "displayName": "mistral-large@2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 128000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-large@2407", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000006, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistral-large@2411-001", "slug": "vertex_ai-mistral_models-vertex_ai-mistral-large-2411-001", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-large@2411-001", "displayName": "mistral-large@2411-001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 128000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-large@2411-001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000006, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistral-large@latest", "slug": "vertex_ai-mistral_models-vertex_ai-mistral-large-latest", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-large@latest", "displayName": "mistral-large@latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 128000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-large@latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000006, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistral-nemo@2407", "slug": "vertex_ai-mistral_models-vertex_ai-mistral-nemo-2407", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-nemo@2407", "displayName": "mistral-nemo@2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-nemo@2407", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistral-nemo@latest", "slug": "vertex_ai-mistral_models-vertex_ai-mistral-nemo-latest", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-nemo@latest", "displayName": "mistral-nemo@latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-nemo@latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-7, "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistral-small-2503", "slug": "vertex_ai-mistral_models-vertex_ai-mistral-small-2503", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-small-2503", "displayName": "mistral-small-2503", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-small-2503", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true } }, { "id": "vertex_ai-mistral_models/vertex_ai/mistral-small-2503@001", "slug": "vertex_ai-mistral_models-vertex_ai-mistral-small-2503-001", "provider": "vertex_ai-mistral_models", "providerSlug": "vertex_ai-mistral_models", "name": "mistral-small-2503@001", "displayName": "mistral-small-2503@001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 8191, "maxInputTokens": 32000, "maxOutputTokens": 8191, "maxTokens": 8191, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-small-2503@001", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "vertex_ai/vertex_ai/mistral-ocr-2505", "slug": "vertex_ai-vertex_ai-mistral-ocr-2505", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "mistral-ocr-2505", "displayName": "mistral-ocr-2505", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": 0.0005, "codeInterpreterUsdPerSession": null, "rawPricing": { "ocr_cost_per_page": 0.0005 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [ "/v1/ocr" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/mistral-ocr-2505", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "rawLitellm": { "litellm_provider": "vertex_ai", "mode": "ocr", "ocr_cost_per_page": 0.0005, "supported_endpoints": [ "/v1/ocr" ], "source": "https://cloud.google.com/generative-ai-app-builder/pricing", "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "vertex_ai/vertex_ai/deepseek-ai/deepseek-ocr-maas", "slug": "vertex_ai-vertex_ai-deepseek-ai-deepseek-ocr-maas", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "deepseek-ocr-maas", "displayName": "deepseek-ocr-maas", "mode": "ocr", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": 0.0003, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "ocr_cost_per_page": 0.0003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "document", "image", "pdf", "text" ], "input": [ "document", "image", "pdf" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/deepseek-ai/deepseek-ocr-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/pricing" }, "rawLitellm": { "litellm_provider": "vertex_ai", "mode": "ocr", "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "ocr_cost_per_page": 0.0003, "source": "https://cloud.google.com/vertex-ai/pricing", "supported_regions": [ "us-central1" ], "manual_modalities_contract_id": "ocr", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "vertex_ai-openai_models/vertex_ai/openai/gpt-oss-120b-maas", "slug": "vertex_ai-openai_models-vertex_ai-openai-gpt-oss-120b-maas", "provider": "vertex_ai-openai_models", "providerSlug": "vertex_ai-openai_models", "name": "gpt-oss-120b-maas", "displayName": "gpt-oss-120b-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/openai/gpt-oss-120b-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-7, "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", "supports_reasoning": true }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "vertex_ai-openai_models/vertex_ai/openai/gpt-oss-20b-maas", "slug": "vertex_ai-openai_models-vertex_ai-openai-gpt-oss-20b-maas", "provider": "vertex_ai-openai_models", "providerSlug": "vertex_ai-openai_models", "name": "gpt-oss-20b-maas", "displayName": "gpt-oss-20b-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/openai/gpt-oss-20b-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas" }, "rawLitellm": { "input_cost_per_token": 7.5e-8, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-7, "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", "supports_reasoning": true }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "vertex_ai/vertex_ai/xai/grok-4.1-fast-non-reasoning", "slug": "vertex_ai-vertex_ai-xai-grok-4-1-fast-non-reasoning", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "grok-4.1-fast-non-reasoning", "displayName": "grok-4.1-fast-non-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/xai/grok-4.1-fast-non-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models (Vertex AI Model Garden)" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 5e-7, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "vertex_ai/vertex_ai/xai/grok-4.1-fast-reasoning", "slug": "vertex_ai-vertex_ai-xai-grok-4-1-fast-reasoning", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "grok-4.1-fast-reasoning", "displayName": "grok-4.1-fast-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/xai/grok-4.1-fast-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models (Vertex AI Model Garden)" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 5e-7, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "vertex_ai/vertex_ai/xai/grok-4.20-non-reasoning", "slug": "vertex_ai-vertex_ai-xai-grok-4-20-non-reasoning", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "grok-4.20-non-reasoning", "displayName": "grok-4.20-non-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/xai/grok-4.20-non-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models (Vertex AI Model Garden)" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "vertex_ai/vertex_ai/xai/grok-4.20-reasoning", "slug": "vertex_ai-vertex_ai-xai-grok-4-20-reasoning", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "grok-4.20-reasoning", "displayName": "grok-4.20-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/xai/grok-4.20-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models (Vertex AI Model Garden)" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "vertex_ai-qwen_models/vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas", "slug": "vertex_ai-qwen_models-vertex_ai-qwen-qwen3-235b-a22b-instruct-2507-maas", "provider": "vertex_ai-qwen_models", "providerSlug": "vertex_ai-qwen_models", "name": "qwen3-235b-a22b-instruct-2507-maas", "displayName": "qwen3-235b-a22b-instruct-2507-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 262144, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "input_cost_per_token": 2.5e-7, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000001, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global", "us-south1" ], "supports_function_calling": true, "supports_tool_choice": true } }, { "id": "vertex_ai-qwen_models/vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas", "slug": "vertex_ai-qwen_models-vertex_ai-qwen-qwen3-coder-480b-a35b-instruct-maas", "provider": "vertex_ai-qwen_models", "providerSlug": "vertex_ai-qwen_models", "name": "qwen3-coder-480b-a35b-instruct-maas", "displayName": "qwen3-coder-480b-a35b-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 262144, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "input_cost_per_token": 0.000001, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000004, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "vertex_ai-qwen_models/vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas", "slug": "vertex_ai-qwen_models-vertex_ai-qwen-qwen3-next-80b-a3b-instruct-maas", "provider": "vertex_ai-qwen_models", "providerSlug": "vertex_ai-qwen_models", "name": "qwen3-next-80b-a3b-instruct-maas", "displayName": "qwen3-next-80b-a3b-instruct-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "vertex_ai-qwen_models/vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas", "slug": "vertex_ai-qwen_models-vertex_ai-qwen-qwen3-next-80b-a3b-thinking-maas", "provider": "vertex_ai-qwen_models", "providerSlug": "vertex_ai-qwen_models", "name": "qwen3-next-80b-a3b-thinking-maas", "displayName": "qwen3-next-80b-a3b-thinking-maas", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_tool_choice": true }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "vertex_ai-video-models/vertex_ai/veo-2.0-generate-001", "slug": "vertex_ai-video-models-vertex_ai-veo-2-0-generate-001", "provider": "vertex_ai-video-models", "providerSlug": "vertex_ai-video-models", "name": "veo-2.0-generate-001", "displayName": "veo-2.0-generate-001", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.35, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.35 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/veo-2.0-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/video" }, "rawLitellm": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.35, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] } }, { "id": "vertex_ai-video-models/vertex_ai/veo-3.0-fast-generate-001", "slug": "vertex_ai-video-models-vertex_ai-veo-3-0-fast-generate-001", "provider": "vertex_ai-video-models", "providerSlug": "vertex_ai-video-models", "name": "veo-3.0-fast-generate-001", "displayName": "veo-3.0-fast-generate-001", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.15, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.15 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/veo-3.0-fast-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/video" }, "rawLitellm": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.15, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] } }, { "id": "vertex_ai-video-models/vertex_ai/veo-3.0-generate-001", "slug": "vertex_ai-video-models-vertex_ai-veo-3-0-generate-001", "provider": "vertex_ai-video-models", "providerSlug": "vertex_ai-video-models", "name": "veo-3.0-generate-001", "displayName": "veo-3.0-generate-001", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.4, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.4 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/veo-3.0-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/video" }, "rawLitellm": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] } }, { "id": "vertex_ai-video-models/vertex_ai/veo-3.1-generate-preview", "slug": "vertex_ai-video-models-vertex_ai-veo-3-1-generate-preview", "provider": "vertex_ai-video-models", "providerSlug": "vertex_ai-video-models", "name": "veo-3.1-generate-preview", "displayName": "veo-3.1-generate-preview", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.4, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.4 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/veo-3.1-generate-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo" }, "rawLitellm": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] } }, { "id": "vertex_ai-video-models/vertex_ai/veo-3.1-fast-generate-preview", "slug": "vertex_ai-video-models-vertex_ai-veo-3-1-fast-generate-preview", "provider": "vertex_ai-video-models", "providerSlug": "vertex_ai-video-models", "name": "veo-3.1-fast-generate-preview", "displayName": "veo-3.1-fast-generate-preview", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.15, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.15 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/veo-3.1-fast-generate-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo" }, "rawLitellm": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.15, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] } }, { "id": "vertex_ai-video-models/vertex_ai/veo-3.1-generate-001", "slug": "vertex_ai-video-models-vertex_ai-veo-3-1-generate-001", "provider": "vertex_ai-video-models", "providerSlug": "vertex_ai-video-models", "name": "veo-3.1-generate-001", "displayName": "veo-3.1-generate-001", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.4, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.4 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/veo-3.1-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo" }, "rawLitellm": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] } }, { "id": "vertex_ai-video-models/vertex_ai/veo-3.1-fast-generate-001", "slug": "vertex_ai-video-models-vertex_ai-veo-3-1-fast-generate-001", "provider": "vertex_ai-video-models", "providerSlug": "vertex_ai-video-models", "name": "veo-3.1-fast-generate-001", "displayName": "veo-3.1-fast-generate-001", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.15, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_second": 0.15 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 1024, "maxOutputTokens": null, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/veo-3.1-fast-generate-001", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo" }, "rawLitellm": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.15, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] } }, { "id": "voyage/voyage/rerank-2", "slug": "voyage-voyage-rerank-2", "provider": "voyage", "providerSlug": "voyage", "name": "rerank-2", "displayName": "rerank-2", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 16000, "maxInputTokens": 16000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 16000, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/rerank-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "voyage", "max_input_tokens": 16000, "max_output_tokens": 16000, "max_query_tokens": 16000, "max_tokens": 16000, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "voyage/voyage/rerank-2-lite", "slug": "voyage-voyage-rerank-2-lite", "provider": "voyage", "providerSlug": "voyage", "name": "rerank-2-lite", "displayName": "rerank-2-lite", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 8000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 8000, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/rerank-2-lite", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-8, "litellm_provider": "voyage", "max_input_tokens": 8000, "max_output_tokens": 8000, "max_query_tokens": 8000, "max_tokens": 8000, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "voyage/voyage/rerank-2.5", "slug": "voyage-voyage-rerank-2-5", "provider": "voyage", "providerSlug": "voyage", "name": "rerank-2.5", "displayName": "rerank-2.5", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 32000, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/rerank-2.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 5e-8, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, "max_query_tokens": 32000, "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "voyage/voyage/rerank-2.5-lite", "slug": "voyage-voyage-rerank-2-5-lite", "provider": "voyage", "providerSlug": "voyage", "name": "rerank-2.5-lite", "displayName": "rerank-2.5-lite", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": 32000, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/rerank-2.5-lite", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-8, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, "max_query_tokens": 32000, "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "voyage/voyage/voyage-2", "slug": "voyage-voyage-voyage-2", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-2", "displayName": "voyage-2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 4000, "maxOutputTokens": null, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "voyage", "max_input_tokens": 4000, "max_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-3", "slug": "voyage-voyage-voyage-3", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-3", "displayName": "voyage-3", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": null, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-3-large", "slug": "voyage-voyage-voyage-3-large", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-3-large", "displayName": "voyage-3-large", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": null, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-3-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.8e-7, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-3-lite", "slug": "voyage-voyage-voyage-3-lite", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-3-lite", "displayName": "voyage-3-lite", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": null, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-3-lite", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-8, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-3.5", "slug": "voyage-voyage-voyage-3-5", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-3.5", "displayName": "voyage-3.5", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": null, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-3.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 6e-8, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-3.5-lite", "slug": "voyage-voyage-voyage-3-5-lite", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-3.5-lite", "displayName": "voyage-3.5-lite", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": null, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-3.5-lite", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-8, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-code-2", "slug": "voyage-voyage-voyage-code-2", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-code-2", "displayName": "voyage-code-2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 16000, "maxInputTokens": 16000, "maxOutputTokens": null, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-code-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "voyage", "max_input_tokens": 16000, "max_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-code-3", "slug": "voyage-voyage-voyage-code-3", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-code-3", "displayName": "voyage-code-3", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": null, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-code-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.8e-7, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-context-3", "slug": "voyage-voyage-voyage-context-3", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-context-3", "displayName": "voyage-context-3", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 120000, "maxInputTokens": 120000, "maxOutputTokens": null, "maxTokens": 120000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-context-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.8e-7, "litellm_provider": "voyage", "max_input_tokens": 120000, "max_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-finance-2", "slug": "voyage-voyage-voyage-finance-2", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-finance-2", "displayName": "voyage-finance-2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": null, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-finance-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-large-2", "slug": "voyage-voyage-voyage-large-2", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-large-2", "displayName": "voyage-large-2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 16000, "maxInputTokens": 16000, "maxOutputTokens": null, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-large-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "voyage", "max_input_tokens": 16000, "max_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-law-2", "slug": "voyage-voyage-voyage-law-2", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-law-2", "displayName": "voyage-law-2", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 16000, "maxInputTokens": 16000, "maxOutputTokens": null, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-law-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "voyage", "max_input_tokens": 16000, "max_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-lite-01", "slug": "voyage-voyage-voyage-lite-01", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-lite-01", "displayName": "voyage-lite-01", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": null, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-lite-01", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "voyage", "max_input_tokens": 4096, "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-lite-02-instruct", "slug": "voyage-voyage-voyage-lite-02-instruct", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-lite-02-instruct", "displayName": "voyage-lite-02-instruct", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4000, "maxInputTokens": 4000, "maxOutputTokens": null, "maxTokens": 4000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-lite-02-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1e-7, "litellm_provider": "voyage", "max_input_tokens": 4000, "max_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "voyage/voyage/voyage-multimodal-3", "slug": "voyage-voyage-voyage-multimodal-3", "provider": "voyage", "providerSlug": "voyage", "name": "voyage-multimodal-3", "displayName": "voyage-multimodal-3", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.12, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.12, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": null, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "voyage/voyage-multimodal-3", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.2e-7, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0 } }, { "id": "wandb/wandb/openai/gpt-oss-120b", "slug": "wandb-wandb-openai-gpt-oss-120b", "provider": "wandb", "providerSlug": "wandb", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 15000, "outputUsdPer1MTokens": 60000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 15000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.015, "output_cost_per_token": 0.06 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/openai/gpt-oss-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 0.015, "output_cost_per_token": 0.06, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "wandb/wandb/openai/gpt-oss-20b", "slug": "wandb-wandb-openai-gpt-oss-20b", "provider": "wandb", "providerSlug": "wandb", "name": "gpt-oss-20b", "displayName": "gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5000, "outputUsdPer1MTokens": 20000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.005, "output_cost_per_token": 0.02 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/openai/gpt-oss-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 0.005, "output_cost_per_token": 0.02, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "wandb/wandb/zai-org/GLM-4.5", "slug": "wandb-wandb-zai-org-glm-4-5", "provider": "wandb", "providerSlug": "wandb", "name": "GLM-4.5", "displayName": "GLM-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 55000, "outputUsdPer1MTokens": 200000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 55000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.055, "output_cost_per_token": 0.2 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/zai-org/GLM-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 0.055, "output_cost_per_token": 0.2, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "wandb/wandb/Qwen/Qwen3-235B-A22B-Instruct-2507", "slug": "wandb-wandb-qwen-qwen3-235b-a22b-instruct-2507", "provider": "wandb", "providerSlug": "wandb", "name": "Qwen3-235B-A22B-Instruct-2507", "displayName": "Qwen3-235B-A22B-Instruct-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10000, "outputUsdPer1MTokens": 10000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.01, "output_cost_per_token": 0.01 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 0.01, "output_cost_per_token": 0.01, "litellm_provider": "wandb", "mode": "chat" } }, { "id": "wandb/wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct", "slug": "wandb-wandb-qwen-qwen3-coder-480b-a35b-instruct", "provider": "wandb", "providerSlug": "wandb", "name": "Qwen3-Coder-480B-A35B-Instruct", "displayName": "Qwen3-Coder-480B-A35B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 100000, "outputUsdPer1MTokens": 150000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 100000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.1, "output_cost_per_token": 0.15 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 0.1, "output_cost_per_token": 0.15, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "wandb/wandb/Qwen/Qwen3-235B-A22B-Thinking-2507", "slug": "wandb-wandb-qwen-qwen3-235b-a22b-thinking-2507", "provider": "wandb", "providerSlug": "wandb", "name": "Qwen3-235B-A22B-Thinking-2507", "displayName": "Qwen3-235B-A22B-Thinking-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 10000, "outputUsdPer1MTokens": 10000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 10000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.01, "output_cost_per_token": 0.01 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 0.01, "output_cost_per_token": 0.01, "litellm_provider": "wandb", "mode": "chat" } }, { "id": "wandb/wandb/moonshotai/Kimi-K2-Instruct", "slug": "wandb-wandb-moonshotai-kimi-k2-instruct", "provider": "wandb", "providerSlug": "wandb", "name": "Kimi-K2-Instruct", "displayName": "Kimi-K2-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/moonshotai/Kimi-K2-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "litellm_provider": "wandb", "mode": "chat" } }, { "id": "wandb/wandb/moonshotai/Kimi-K2.5", "slug": "wandb-wandb-moonshotai-kimi-k2-5", "provider": "wandb", "providerSlug": "wandb", "name": "Kimi-K2.5", "displayName": "Kimi-K2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": 0.09999999999999999, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/moonshotai/Kimi-K2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://wandb.ai/inference/coreweave/cw_moonshotai_Kimi-K2.5" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003, "litellm_provider": "wandb", "mode": "chat", "source": "https://wandb.ai/inference/coreweave/cw_moonshotai_Kimi-K2.5", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "benchmarks": { "gpqadiamond_score_kimik25_officialmodelcard_170": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.6, "scoreText": "87.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "livecodebenchv6_pass1_kimik25_officialmodelcard_171": { "label": "LiveCodeBench v6", "category": "coding", "score": 85, "scoreText": "85.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_swebenchpro_score_kimik25_officialmodelcard_219": { "label": "SWE-bench Pro", "category": "coding", "score": 50.7, "scoreText": "50.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Kimi-K2.5 evaluation results section on the HF page." }, "local_swebenchresolved_score_kimik25_officialmodelcard_220": { "label": "SWE-bench Verified", "category": "coding", "score": 70.8, "scoreText": "70.8 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_terminalbench2_score_kimik25_officialmodelcard_221": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 43.2, "scoreText": "43.2 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_apexagents_score_kimik25_officialmodelcard_222": { "label": "Apex Agents", "category": "other", "score": 14.4, "scoreText": "14.4 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/moonshotai/Kimi-K2.5", "checked_at": "2026-05-31", "baseModelFamily": "Kimi-K2.5", "exactModelOrSnapshot": "Kimi-K2.5", "modelDeveloper": "Moonshot AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Asterisk is preserved from the source page." }, "local_artificialanalysisintelligenceindex_score_moonshotaikimik25_benchmarkleaderboard_316": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 46.8, "scoreText": "46.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysiscodingindex_score_moonshotaikimik25_benchmarkleaderboard_317": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 39.6, "scoreText": "39.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." }, "local_artificialanalysisagenticindex_score_moonshotaikimik25_benchmarkleaderboard_318": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 58.9, "scoreText": "58.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/moonshotai/kimi-k2.5", "checked_at": "2026-05-31", "baseModelFamily": "kimi-k2.5", "exactModelOrSnapshot": "moonshotai/kimi-k2.5", "modelDeveloper": "Moonshot AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page; HF card separately states Modified MIT and 1.1T parameters." } } }, { "id": "wandb/wandb/MiniMaxAI/MiniMax-M2.5", "slug": "wandb-wandb-minimaxai-minimax-m2-5", "provider": "wandb", "providerSlug": "wandb", "name": "MiniMax-M2.5", "displayName": "MiniMax-M2.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 197000, "maxInputTokens": 197000, "maxOutputTokens": 197000, "maxTokens": 197000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/MiniMaxAI/MiniMax-M2.5", "syncedAt": "2026-05-28", "sourceUrl": "https://wandb.ai/inference/coreweave/cw_MiniMaxAI_MiniMax-M2.5" }, "rawLitellm": { "max_tokens": 197000, "max_input_tokens": 197000, "max_output_tokens": 197000, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "litellm_provider": "wandb", "mode": "chat", "source": "https://wandb.ai/inference/coreweave/cw_MiniMaxAI_MiniMax-M2.5", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true }, "benchmarks": { "swebenchverified_resolved_minimaxm25highreasoning_benchmarkleaderboard_216": { "label": "SWE-bench Verified", "category": "coding", "score": 75.8, "scoreText": "75.80%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax M2.5", "exactModelOrSnapshot": "MiniMax M2.5 (high reasoning)", "modelDeveloper": "MiniMax", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "wandb/wandb/meta-llama/Llama-3.1-8B-Instruct", "slug": "wandb-wandb-meta-llama-llama-3-1-8b-instruct", "provider": "wandb", "providerSlug": "wandb", "name": "Llama-3.1-8B-Instruct", "displayName": "Llama-3.1-8B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 22000, "outputUsdPer1MTokens": 22000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 22000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.022, "output_cost_per_token": 0.022 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/meta-llama/Llama-3.1-8B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 0.022, "output_cost_per_token": 0.022, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "wandb/wandb/deepseek-ai/DeepSeek-V3.1", "slug": "wandb-wandb-deepseek-ai-deepseek-v3-1", "provider": "wandb", "providerSlug": "wandb", "name": "DeepSeek-V3.1", "displayName": "DeepSeek-V3.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 55000, "outputUsdPer1MTokens": 165000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 55000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.055, "output_cost_per_token": 0.165 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/deepseek-ai/DeepSeek-V3.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 0.055, "output_cost_per_token": 0.165, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "wandb/wandb/deepseek-ai/DeepSeek-R1-0528", "slug": "wandb-wandb-deepseek-ai-deepseek-r1-0528", "provider": "wandb", "providerSlug": "wandb", "name": "DeepSeek-R1-0528", "displayName": "DeepSeek-R1-0528", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 135000, "outputUsdPer1MTokens": 540000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 135000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.135, "output_cost_per_token": 0.54 } }, "limits": { "contextWindow": 161000, "maxInputTokens": 161000, "maxOutputTokens": 161000, "maxTokens": 161000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/deepseek-ai/DeepSeek-R1-0528", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 161000, "max_input_tokens": 161000, "max_output_tokens": 161000, "input_cost_per_token": 0.135, "output_cost_per_token": 0.54, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "wandb/wandb/deepseek-ai/DeepSeek-V3-0324", "slug": "wandb-wandb-deepseek-ai-deepseek-v3-0324", "provider": "wandb", "providerSlug": "wandb", "name": "DeepSeek-V3-0324", "displayName": "DeepSeek-V3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 114000, "outputUsdPer1MTokens": 275000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 114000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.114, "output_cost_per_token": 0.275 } }, "limits": { "contextWindow": 161000, "maxInputTokens": 161000, "maxOutputTokens": 161000, "maxTokens": 161000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/deepseek-ai/DeepSeek-V3-0324", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 161000, "max_input_tokens": 161000, "max_output_tokens": 161000, "input_cost_per_token": 0.114, "output_cost_per_token": 0.275, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "wandb/wandb/meta-llama/Llama-3.3-70B-Instruct", "slug": "wandb-wandb-meta-llama-llama-3-3-70b-instruct", "provider": "wandb", "providerSlug": "wandb", "name": "Llama-3.3-70B-Instruct", "displayName": "Llama-3.3-70B-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 71000, "outputUsdPer1MTokens": 71000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 71000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.071, "output_cost_per_token": 0.071 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/meta-llama/Llama-3.3-70B-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 0.071, "output_cost_per_token": 0.071, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "wandb/wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct", "slug": "wandb-wandb-meta-llama-llama-4-scout-17b-16e-instruct", "provider": "wandb", "providerSlug": "wandb", "name": "Llama-4-Scout-17B-16E-Instruct", "displayName": "Llama-4-Scout-17B-16E-Instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 17000, "outputUsdPer1MTokens": 66000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 17000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.017, "output_cost_per_token": 0.066 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 64000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 64000, "max_input_tokens": 64000, "max_output_tokens": 64000, "input_cost_per_token": 0.017, "output_cost_per_token": 0.066, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "wandb/wandb/microsoft/Phi-4-mini-instruct", "slug": "wandb-wandb-microsoft-phi-4-mini-instruct", "provider": "wandb", "providerSlug": "wandb", "name": "Phi-4-mini-instruct", "displayName": "Phi-4-mini-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 8000, "outputUsdPer1MTokens": 35000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 8000, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.008, "output_cost_per_token": 0.035 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "wandb/microsoft/Phi-4-mini-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 0.008, "output_cost_per_token": 0.035, "litellm_provider": "wandb", "mode": "chat" }, "benchmarks": { "mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_202": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "gpqa_science_phi414b_officialmodelcard_203": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "humaneval_codegeneration_phi414b_officialmodelcard_204": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "drop_reasoning_phi414b_officialmodelcard_205": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card; selected the phi-4 (14B) column from the quality table." }, "local_mmlu_popularaggregatedbenchmark_phi414b_officialmodelcard_160": { "label": "MMLU", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "Popular Aggregated Benchmark", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_gpqa_science_phi414b_officialmodelcard_161": { "label": "GPQA", "category": "science", "score": 56.1, "scoreText": "56.1", "metric": "Science", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_humaneval_codegeneration_phi414b_officialmodelcard_162": { "label": "HumanEval", "category": "coding", "score": 82.6, "scoreText": "82.6", "metric": "Code Generation", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_simpleqa_factualknowledge_phi414b_officialmodelcard_163": { "label": "SimpleQA", "category": "general_knowledge", "score": 3, "scoreText": "3.0", "metric": "Factual Knowledge", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." }, "local_drop_reasoning_phi414b_officialmodelcard_164": { "label": "DROP", "category": "reasoning", "score": 75.5, "scoreText": "75.5", "metric": "Reasoning", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/phi-4", "checked_at": "2026-05-31", "baseModelFamily": "Phi-4", "exactModelOrSnapshot": "phi-4 (14B)", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-4 model card comparison table; selected the phi-4 (14B) column." } } }, { "id": "watsonx/watsonx/ibm/granite-3-8b-instruct", "slug": "watsonx-watsonx-ibm-granite-3-8b-instruct", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-3-8b-instruct", "displayName": "granite-3-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 1024, "maxInputTokens": 8192, "maxOutputTokens": 1024, "maxTokens": 1024, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": false, "audio_output": false, "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-3-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 2e-7, "litellm_provider": "watsonx", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 2e-7, "supports_audio_input": false, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false } }, { "id": "watsonx/watsonx/mistralai/mistral-large", "slug": "watsonx-watsonx-mistralai-mistral-large", "provider": "watsonx", "providerSlug": "watsonx", "name": "mistral-large", "displayName": "mistral-large", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 131072, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": false, "audio_output": false, "function_calling": true, "parallel_function_calling": false, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/mistralai/mistral-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "watsonx", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00001, "supports_audio_input": false, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false } }, { "id": "watsonx/watsonx/bigscience/mt0-xxl-13b", "slug": "watsonx-watsonx-bigscience-mt0-xxl-13b", "provider": "watsonx", "providerSlug": "watsonx", "name": "mt0-xxl-13b", "displayName": "mt0-xxl-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 500, "outputUsdPer1MTokens": 2000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 500, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0005, "output_cost_per_token": 0.002 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/bigscience/mt0-xxl-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 0.0005, "output_cost_per_token": 0.002, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/core42/jais-13b-chat", "slug": "watsonx-watsonx-core42-jais-13b-chat", "provider": "watsonx", "providerSlug": "watsonx", "name": "jais-13b-chat", "displayName": "jais-13b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 500, "outputUsdPer1MTokens": 2000, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 500, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0005, "output_cost_per_token": 0.002 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/core42/jais-13b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 0.0005, "output_cost_per_token": 0.002, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/google/flan-t5-xl-3b", "slug": "watsonx-watsonx-google-flan-t5-xl-3b", "provider": "watsonx", "providerSlug": "watsonx", "name": "flan-t5-xl-3b", "displayName": "flan-t5-xl-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/google/flan-t5-xl-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/ibm/granite-13b-chat-v2", "slug": "watsonx-watsonx-ibm-granite-13b-chat-v2", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-13b-chat-v2", "displayName": "granite-13b-chat-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-13b-chat-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/ibm/granite-13b-instruct-v2", "slug": "watsonx-watsonx-ibm-granite-13b-instruct-v2", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-13b-instruct-v2", "displayName": "granite-13b-instruct-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-13b-instruct-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/ibm/granite-3-3-8b-instruct", "slug": "watsonx-watsonx-ibm-granite-3-3-8b-instruct", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-3-3-8b-instruct", "displayName": "granite-3-3-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-3-3-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false } }, { "id": "watsonx/watsonx/ibm/granite-4-h-small", "slug": "watsonx-watsonx-ibm-granite-4-h-small", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-4-h-small", "displayName": "granite-4-h-small", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 20480, "maxInputTokens": 20480, "maxOutputTokens": 20480, "maxTokens": 20480, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-4-h-small", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 20480, "max_input_tokens": 20480, "max_output_tokens": 20480, "input_cost_per_token": 6e-8, "output_cost_per_token": 2.5e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false } }, { "id": "watsonx/watsonx/ibm/granite-guardian-3-2-2b", "slug": "watsonx-watsonx-ibm-granite-guardian-3-2-2b", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-guardian-3-2-2b", "displayName": "granite-guardian-3-2-2b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-guardian-3-2-2b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/ibm/granite-guardian-3-3-8b", "slug": "watsonx-watsonx-ibm-granite-guardian-3-3-8b", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-guardian-3-3-8b", "displayName": "granite-guardian-3-3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-guardian-3-3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/ibm/granite-ttm-1024-96-r2", "slug": "watsonx-watsonx-ibm-granite-ttm-1024-96-r2", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-ttm-1024-96-r2", "displayName": "granite-ttm-1024-96-r2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.38, "outputUsdPer1MTokens": 0.38, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.8e-7, "output_cost_per_token": 3.8e-7 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": 512, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-ttm-1024-96-r2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-7, "output_cost_per_token": 3.8e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/ibm/granite-ttm-1536-96-r2", "slug": "watsonx-watsonx-ibm-granite-ttm-1536-96-r2", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-ttm-1536-96-r2", "displayName": "granite-ttm-1536-96-r2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.38, "outputUsdPer1MTokens": 0.38, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.8e-7, "output_cost_per_token": 3.8e-7 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": 512, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-ttm-1536-96-r2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-7, "output_cost_per_token": 3.8e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/ibm/granite-ttm-512-96-r2", "slug": "watsonx-watsonx-ibm-granite-ttm-512-96-r2", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-ttm-512-96-r2", "displayName": "granite-ttm-512-96-r2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.38, "outputUsdPer1MTokens": 0.38, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.8e-7, "output_cost_per_token": 3.8e-7 } }, "limits": { "contextWindow": 512, "maxInputTokens": 512, "maxOutputTokens": 512, "maxTokens": 512, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-ttm-512-96-r2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-7, "output_cost_per_token": 3.8e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/ibm/granite-vision-3-2-2b", "slug": "watsonx-watsonx-ibm-granite-vision-3-2-2b", "provider": "watsonx", "providerSlug": "watsonx", "name": "granite-vision-3-2-2b", "displayName": "granite-vision-3-2-2b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/ibm/granite-vision-3-2-2b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true } }, { "id": "watsonx/watsonx/meta-llama/llama-3-2-11b-vision-instruct", "slug": "watsonx-watsonx-meta-llama-llama-3-2-11b-vision-instruct", "provider": "watsonx", "providerSlug": "watsonx", "name": "llama-3-2-11b-vision-instruct", "displayName": "llama-3-2-11b-vision-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 0.35, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/meta-llama/llama-3-2-11b-vision-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "watsonx/watsonx/meta-llama/llama-3-2-1b-instruct", "slug": "watsonx-watsonx-meta-llama-llama-3-2-1b-instruct", "provider": "watsonx", "providerSlug": "watsonx", "name": "llama-3-2-1b-instruct", "displayName": "llama-3-2-1b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/meta-llama/llama-3-2-1b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "watsonx/watsonx/meta-llama/llama-3-2-3b-instruct", "slug": "watsonx-watsonx-meta-llama-llama-3-2-3b-instruct", "provider": "watsonx", "providerSlug": "watsonx", "name": "llama-3-2-3b-instruct", "displayName": "llama-3-2-3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/meta-llama/llama-3-2-3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "watsonx/watsonx/meta-llama/llama-3-2-90b-vision-instruct", "slug": "watsonx-watsonx-meta-llama-llama-3-2-90b-vision-instruct", "provider": "watsonx", "providerSlug": "watsonx", "name": "llama-3-2-90b-vision-instruct", "displayName": "llama-3-2-90b-vision-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/meta-llama/llama-3-2-90b-vision-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "watsonx/watsonx/meta-llama/llama-3-3-70b-instruct", "slug": "watsonx-watsonx-meta-llama-llama-3-3-70b-instruct", "provider": "watsonx", "providerSlug": "watsonx", "name": "llama-3-3-70b-instruct", "displayName": "llama-3-3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.71, "outputUsdPer1MTokens": 0.71, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.71, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.1e-7, "output_cost_per_token": 7.1e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/meta-llama/llama-3-3-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.1e-7, "output_cost_per_token": 7.1e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "watsonx/watsonx/meta-llama/llama-4-maverick-17b", "slug": "watsonx-watsonx-meta-llama-llama-4-maverick-17b", "provider": "watsonx", "providerSlug": "watsonx", "name": "llama-4-maverick-17b", "displayName": "llama-4-maverick-17b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 1.4, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.0000014 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/meta-llama/llama-4-maverick-17b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.0000014, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "watsonx/watsonx/meta-llama/llama-guard-3-11b-vision", "slug": "watsonx-watsonx-meta-llama-llama-guard-3-11b-vision", "provider": "watsonx", "providerSlug": "watsonx", "name": "llama-guard-3-11b-vision", "displayName": "llama-guard-3-11b-vision", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 0.35, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/meta-llama/llama-guard-3-11b-vision", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true } }, { "id": "watsonx/watsonx/mistralai/mistral-medium-2505", "slug": "watsonx-watsonx-mistralai-mistral-medium-2505", "provider": "watsonx", "providerSlug": "watsonx", "name": "mistral-medium-2505", "displayName": "mistral-medium-2505", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/mistralai/mistral-medium-2505", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.00001, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false } }, { "id": "watsonx/watsonx/mistralai/mistral-small-2503", "slug": "watsonx-watsonx-mistralai-mistral-small-2503", "provider": "watsonx", "providerSlug": "watsonx", "name": "mistral-small-2503", "displayName": "mistral-small-2503", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/mistralai/mistral-small-2503", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false } }, { "id": "watsonx/watsonx/mistralai/mistral-small-3-1-24b-instruct-2503", "slug": "watsonx-watsonx-mistralai-mistral-small-3-1-24b-instruct-2503", "provider": "watsonx", "providerSlug": "watsonx", "name": "mistral-small-3-1-24b-instruct-2503", "displayName": "mistral-small-3-1-24b-instruct-2503", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false }, "benchmarks": { "mmlu_accuracy_mistralsmall3_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 81, "scoreText": "81%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mistral-small-3", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3", "exactModelOrSnapshot": "mistral-small-3", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact score is stated in the announcement text." }, "local_mmlu_accuracy_mistralsmall3124binstruct2503_officialmodelcard_281": { "label": "MMLU", "category": "general_knowledge", "score": 80.62, "scoreText": "80.62%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3.1", "exactModelOrSnapshot": "Mistral-Small-3.1-24B-Instruct-2503", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "medium", "note": "Instruction eval table in the model card; percentages are printed as-is." }, "local_math_accuracy_mistralsmall3124binstruct2503_officialmodelcard_282": { "label": "MATH", "category": "math", "score": 69.3, "scoreText": "69.30%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3.1", "exactModelOrSnapshot": "Mistral-Small-3.1-24B-Instruct-2503", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "medium", "note": "Instruction eval table in the model card; percentages are printed as-is." }, "local_humaneval_pass1_mistralsmall3124binstruct2503_officialmodelcard_283": { "label": "HumanEval", "category": "coding", "score": 88.41, "scoreText": "88.41%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3.1", "exactModelOrSnapshot": "Mistral-Small-3.1-24B-Instruct-2503", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "medium", "note": "Instruction eval table in the model card; percentages are printed as-is." }, "local_longbenchv2_score_mistralsmall3124binstruct2503_officialmodelcard_284": { "label": "LongBench v2", "category": "long_context", "score": 37.18, "scoreText": "37.18%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Small 3.1", "exactModelOrSnapshot": "Mistral-Small-3.1-24B-Instruct-2503", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "medium", "note": "Long-context eval table in the model card; percentages are printed as-is." } } }, { "id": "watsonx/watsonx/mistralai/pixtral-12b-2409", "slug": "watsonx-watsonx-mistralai-pixtral-12b-2409", "provider": "watsonx", "providerSlug": "watsonx", "name": "pixtral-12b-2409", "displayName": "pixtral-12b-2409", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.35, "outputUsdPer1MTokens": 0.35, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.35, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/mistralai/pixtral-12b-2409", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true } }, { "id": "watsonx/watsonx/openai/gpt-oss-120b", "slug": "watsonx-watsonx-openai-gpt-oss-120b", "provider": "watsonx", "providerSlug": "watsonx", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/openai/gpt-oss-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "watsonx/watsonx/sdaia/allam-1-13b-instruct", "slug": "watsonx-watsonx-sdaia-allam-1-13b-instruct", "provider": "watsonx", "providerSlug": "watsonx", "name": "allam-1-13b-instruct", "displayName": "allam-1-13b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.7999999999999998, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.7999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.0000018 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": false, "parallel_function_calling": false, "vision": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/sdaia/allam-1-13b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.0000018, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false } }, { "id": "watsonx/watsonx/whisper-large-v3-turbo", "slug": "watsonx-watsonx-whisper-large-v3-turbo", "provider": "watsonx", "providerSlug": "watsonx", "name": "whisper-large-v3-turbo", "displayName": "whisper-large-v3-turbo", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0001, "perSecondOutputUsd": 0.0001, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "watsonx/whisper-large-v3-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001, "litellm_provider": "watsonx", "mode": "audio_transcription", "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "openai/whisper-1", "slug": "openai-whisper-1", "provider": "OpenAI", "providerSlug": "openai", "name": "whisper-1", "displayName": "whisper-1", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": 0.0001, "perSecondOutputUsd": 0.0001, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "whisper-1", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_second": 0.0001, "litellm_provider": "openai", "mode": "audio_transcription", "output_cost_per_second": 0.0001, "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "xai/xai/grok-2", "slug": "xai-xai-grok-2", "provider": "xai", "providerSlug": "xai", "name": "grok-2", "displayName": "grok-2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-2", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/release-notes" ], "manual_model_modalities_note": "xAI Grok 2 text-only exact ids from official docs" }, "benchmarks": { "gpqa_accuracy_grok2_officiallaunchpost_105": { "label": "GPQA", "category": "general_knowledge", "score": 56, "scoreText": "56.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlu_accuracy_grok2_officiallaunchpost_106": { "label": "MMLU", "category": "general_knowledge", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlupro_accuracy_grok2_officiallaunchpost_107": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "math_accuracy_grok2_officiallaunchpost_108": { "label": "MATH", "category": "math", "score": 76.1, "scoreText": "76.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "humaneval_pass1_grok2_officiallaunchpost_109": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 HumanEval is reported as pass@1." }, "mmmu_accuracy_grok2_officiallaunchpost_110": { "label": "MMMU", "category": "multimodal", "score": 66.1, "scoreText": "66.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." } } }, { "id": "xai/xai/grok-2-1212", "slug": "xai-xai-grok-2-1212", "provider": "xai", "providerSlug": "xai", "name": "grok-2-1212", "displayName": "grok-2-1212", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-2-1212", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/release-notes" ], "manual_model_modalities_note": "xAI Grok 2 text-only exact ids from official docs" }, "benchmarks": { "gpqa_accuracy_grok2_officiallaunchpost_105": { "label": "GPQA", "category": "general_knowledge", "score": 56, "scoreText": "56.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlu_accuracy_grok2_officiallaunchpost_106": { "label": "MMLU", "category": "general_knowledge", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlupro_accuracy_grok2_officiallaunchpost_107": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "math_accuracy_grok2_officiallaunchpost_108": { "label": "MATH", "category": "math", "score": 76.1, "scoreText": "76.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "humaneval_pass1_grok2_officiallaunchpost_109": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 HumanEval is reported as pass@1." }, "mmmu_accuracy_grok2_officiallaunchpost_110": { "label": "MMMU", "category": "multimodal", "score": 66.1, "scoreText": "66.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." } } }, { "id": "xai/xai/grok-2-latest", "slug": "xai-xai-grok-2-latest", "provider": "xai", "providerSlug": "xai", "name": "grok-2-latest", "displayName": "grok-2-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-2-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000002, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/release-notes" ], "manual_model_modalities_note": "xAI Grok 2 text-only exact ids from official docs" }, "benchmarks": { "gpqa_accuracy_grok2_officiallaunchpost_105": { "label": "GPQA", "category": "general_knowledge", "score": 56, "scoreText": "56.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlu_accuracy_grok2_officiallaunchpost_106": { "label": "MMLU", "category": "general_knowledge", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlupro_accuracy_grok2_officiallaunchpost_107": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "math_accuracy_grok2_officiallaunchpost_108": { "label": "MATH", "category": "math", "score": 76.1, "scoreText": "76.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "humaneval_pass1_grok2_officiallaunchpost_109": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 HumanEval is reported as pass@1." }, "mmmu_accuracy_grok2_officiallaunchpost_110": { "label": "MMMU", "category": "multimodal", "score": 66.1, "scoreText": "66.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." } } }, { "id": "xai/xai/grok-2-vision", "slug": "xai-xai-grok-2-vision", "provider": "xai", "providerSlug": "xai", "name": "grok-2-vision", "displayName": "grok-2-vision", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 2, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.000002, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-2-vision", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.000002, "input_cost_per_token": 0.000002, "litellm_provider": "xai", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/rest-api-reference/inference/models" ], "manual_model_modalities_note": "xAI Grok 2 Vision exact ids from official docs" }, "benchmarks": { "gpqa_accuracy_grok2_officiallaunchpost_105": { "label": "GPQA", "category": "general_knowledge", "score": 56, "scoreText": "56.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlu_accuracy_grok2_officiallaunchpost_106": { "label": "MMLU", "category": "general_knowledge", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlupro_accuracy_grok2_officiallaunchpost_107": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "math_accuracy_grok2_officiallaunchpost_108": { "label": "MATH", "category": "math", "score": 76.1, "scoreText": "76.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "humaneval_pass1_grok2_officiallaunchpost_109": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 HumanEval is reported as pass@1." }, "mmmu_accuracy_grok2_officiallaunchpost_110": { "label": "MMMU", "category": "multimodal", "score": 66.1, "scoreText": "66.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." } } }, { "id": "xai/xai/grok-2-vision-1212", "slug": "xai-xai-grok-2-vision-1212", "provider": "xai", "providerSlug": "xai", "name": "grok-2-vision-1212", "displayName": "grok-2-vision-1212", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 2, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.000002, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-02-28" }, "source": { "type": "litellm", "litellmKey": "xai/grok-2-vision-1212", "syncedAt": "2026-05-28" }, "rawLitellm": { "deprecation_date": "2026-02-28", "input_cost_per_image": 0.000002, "input_cost_per_token": 0.000002, "litellm_provider": "xai", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/rest-api-reference/inference/models" ], "manual_model_modalities_note": "xAI Grok 2 Vision exact ids from official docs" }, "benchmarks": { "gpqa_accuracy_grok2_officiallaunchpost_105": { "label": "GPQA", "category": "general_knowledge", "score": 56, "scoreText": "56.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlu_accuracy_grok2_officiallaunchpost_106": { "label": "MMLU", "category": "general_knowledge", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlupro_accuracy_grok2_officiallaunchpost_107": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "math_accuracy_grok2_officiallaunchpost_108": { "label": "MATH", "category": "math", "score": 76.1, "scoreText": "76.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "humaneval_pass1_grok2_officiallaunchpost_109": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 HumanEval is reported as pass@1." }, "mmmu_accuracy_grok2_officiallaunchpost_110": { "label": "MMMU", "category": "multimodal", "score": 66.1, "scoreText": "66.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." } } }, { "id": "xai/xai/grok-2-vision-latest", "slug": "xai-xai-grok-2-vision-latest", "provider": "xai", "providerSlug": "xai", "name": "grok-2-vision-latest", "displayName": "grok-2-vision-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 2, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.000002, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-2-vision-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.000002, "input_cost_per_token": 0.000002, "litellm_provider": "xai", "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/rest-api-reference/inference/models" ], "manual_model_modalities_note": "xAI Grok 2 Vision exact ids from official docs" }, "benchmarks": { "gpqa_accuracy_grok2_officiallaunchpost_105": { "label": "GPQA", "category": "general_knowledge", "score": 56, "scoreText": "56.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlu_accuracy_grok2_officiallaunchpost_106": { "label": "MMLU", "category": "general_knowledge", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "mmlupro_accuracy_grok2_officiallaunchpost_107": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "math_accuracy_grok2_officiallaunchpost_108": { "label": "MATH", "category": "math", "score": 76.1, "scoreText": "76.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." }, "humaneval_pass1_grok2_officiallaunchpost_109": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 HumanEval is reported as pass@1." }, "mmmu_accuracy_grok2_officiallaunchpost_110": { "label": "MMMU", "category": "multimodal", "score": 66.1, "scoreText": "66.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-2", "checked_at": "2026-05-31", "baseModelFamily": "grok-2", "exactModelOrSnapshot": "Grok-2", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table; Grok-2 MMLU, MMLU-Pro, MMMU and MathVista were evaluated using 0-shot CoT, and MATH uses maj@1." } } }, { "id": "xai/xai/grok-3", "slug": "xai-xai-grok-3", "provider": "xai", "providerSlug": "xai", "name": "grok-3", "displayName": "grok-3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.75, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-05-15", "shutdownDate": "2026-05-15", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "source": { "type": "litellm", "litellmKey": "xai/grok-3", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 0.000003, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-fast" ], "manual_model_modalities_note": "xAI Grok 3 / Grok 3 Fast exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-3-beta", "slug": "xai-xai-grok-3-beta", "provider": "xai", "providerSlug": "xai", "name": "grok-3-beta", "displayName": "grok-3-beta", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.75, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-3-beta", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 0.000003, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-fast" ], "manual_model_modalities_note": "xAI Grok 3 / Grok 3 Fast exact ids from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-3-fast-beta", "slug": "xai-xai-grok-3-fast-beta", "provider": "xai", "providerSlug": "xai", "name": "grok-3-fast-beta", "displayName": "grok-3-fast-beta", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-3-fast-beta", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000025, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-fast" ], "manual_model_modalities_note": "xAI Grok 3 / Grok 3 Fast exact ids from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-3-fast-latest", "slug": "xai-xai-grok-3-fast-latest", "provider": "xai", "providerSlug": "xai", "name": "grok-3-fast-latest", "displayName": "grok-3-fast-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 25, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-3-fast-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.000005, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000025, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-fast" ], "manual_model_modalities_note": "xAI Grok 3 / Grok 3 Fast exact ids from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-3-latest", "slug": "xai-xai-grok-3-latest", "provider": "xai", "providerSlug": "xai", "name": "grok-3-latest", "displayName": "grok-3-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.75, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-3-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 0.000003, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-fast" ], "manual_model_modalities_note": "xAI Grok 3 / Grok 3 Fast exact ids from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-3-mini", "slug": "xai-xai-grok-3-mini", "provider": "xai", "providerSlug": "xai", "name": "grok-3-mini", "displayName": "grok-3-mini", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-02-28" }, "source": { "type": "litellm", "litellmKey": "xai/grok-3-mini", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "deprecation_date": "2026-02-28", "input_cost_per_token": 3e-7, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-7, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-mini" ], "manual_model_modalities_note": "xAI Grok 3 Mini exact ids from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-3-mini-beta", "slug": "xai-xai-grok-3-mini-beta", "provider": "xai", "providerSlug": "xai", "name": "grok-3-mini-beta", "displayName": "grok-3-mini-beta", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-02-28" }, "source": { "type": "litellm", "litellmKey": "xai/grok-3-mini-beta", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "deprecation_date": "2026-02-28", "input_cost_per_token": 3e-7, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-7, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-mini" ], "manual_model_modalities_note": "xAI Grok 3 Mini exact ids from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-3-mini-fast", "slug": "xai-xai-grok-3-mini-fast", "provider": "xai", "providerSlug": "xai", "name": "grok-3-mini-fast", "displayName": "grok-3-mini-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-3-mini-fast", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000004, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-mini" ], "manual_model_modalities_note": "xAI Grok 3 Mini exact ids from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-3-mini-fast-beta", "slug": "xai-xai-grok-3-mini-fast-beta", "provider": "xai", "providerSlug": "xai", "name": "grok-3-mini-fast-beta", "displayName": "grok-3-mini-fast-beta", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-3-mini-fast-beta", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000004, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-mini" ], "manual_model_modalities_note": "xAI Grok 3 Mini exact ids from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-3-mini-fast-latest", "slug": "xai-xai-grok-3-mini-fast-latest", "provider": "xai", "providerSlug": "xai", "name": "grok-3-mini-fast-latest", "displayName": "grok-3-mini-fast-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 4, "cachedInputUsdPer1MTokens": 0.15, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000004 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-3-mini-fast-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000004, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-mini" ], "manual_model_modalities_note": "xAI Grok 3 Mini exact ids from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-3-mini-latest", "slug": "xai-xai-grok-3-mini-latest", "provider": "xai", "providerSlug": "xai", "name": "grok-3-mini-latest", "displayName": "grok-3-mini-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.075, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": false, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-3-mini-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://x.ai/api#pricing" }, "rawLitellm": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-7, "source": "https://x.ai/api#pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-3-mini" ], "manual_model_modalities_note": "xAI Grok 3 Mini exact ids from official docs" }, "benchmarks": { "aime24_accuracy_grok3beta_officiallaunchpost_111": { "label": "AIME 2024", "category": "math", "score": 52.2, "scoreText": "52.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "gpqa_accuracy_grok3beta_officiallaunchpost_112": { "label": "GPQA", "category": "general_knowledge", "score": 75.4, "scoreText": "75.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." }, "mmlupro_accuracy_grok3beta_officiallaunchpost_113": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 79.9, "scoreText": "79.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-3", "checked_at": "2026-05-31", "baseModelFamily": "grok-3", "exactModelOrSnapshot": "Grok 3 Beta", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI benchmark table for Grok 3 Beta and Grok 3 mini Beta." } } }, { "id": "xai/xai/grok-4", "slug": "xai-xai-grok-4", "provider": "xai", "providerSlug": "xai", "name": "grok-4", "displayName": "grok-4", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "input_cost_per_token": 0.000003, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000015, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.3" ], "manual_model_modalities_note": "xAI Grok 4 family exact ids from official docs" }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4-fast-reasoning", "slug": "xai-xai-grok-4-fast-reasoning", "provider": "xai", "providerSlug": "xai", "name": "grok-4-fast-reasoning", "displayName": "grok-4-fast-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": 0.39999999999999997, "above128kOutputUsdPer1MTokens": 1, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-05-15", "shutdownDate": "2026-05-15", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "source": { "type": "litellm", "litellmKey": "xai/grok-4-fast-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.3" ], "manual_model_modalities_note": "xAI Grok 4 family exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4-fast-non-reasoning", "slug": "xai-xai-grok-4-fast-non-reasoning", "provider": "xai", "providerSlug": "xai", "name": "grok-4-fast-non-reasoning", "displayName": "grok-4-fast-non-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": 0.39999999999999997, "above128kOutputUsdPer1MTokens": 1, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-05-15", "shutdownDate": "2026-05-15", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "source": { "type": "litellm", "litellmKey": "xai/grok-4-fast-non-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.3" ], "manual_model_modalities_note": "xAI Grok 4 family exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4-0709", "slug": "xai-xai-grok-4-0709", "provider": "xai", "providerSlug": "xai", "name": "grok-4-0709", "displayName": "grok-4-0709", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": 6, "above128kOutputUsdPer1MTokens": 30, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "input_cost_per_token_above_128k_tokens": 0.000006, "output_cost_per_token": 0.000015, "output_cost_per_token_above_128k_tokens": 0.00003 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-05-15", "shutdownDate": "2026-05-15", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "source": { "type": "litellm", "litellmKey": "xai/grok-4-0709", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "input_cost_per_token": 0.000003, "input_cost_per_token_above_128k_tokens": 0.000006, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_above_128k_tokens": 0.00003, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.3" ], "manual_model_modalities_note": "xAI Grok 4 family exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4-latest", "slug": "xai-xai-grok-4-latest", "provider": "xai", "providerSlug": "xai", "name": "grok-4-latest", "displayName": "grok-4-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": 6, "above128kOutputUsdPer1MTokens": 30, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000003, "input_cost_per_token_above_128k_tokens": 0.000006, "output_cost_per_token": 0.000015, "output_cost_per_token_above_128k_tokens": 0.00003 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "tool_choice": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "input_cost_per_token": 0.000003, "input_cost_per_token_above_128k_tokens": 0.000006, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000015, "output_cost_per_token_above_128k_tokens": 0.00003, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.3" ], "manual_model_modalities_note": "xAI Grok 4 family exact ids from official docs" }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4-1-fast", "slug": "xai-xai-grok-4-1-fast", "provider": "xai", "providerSlug": "xai", "name": "grok-4-1-fast", "displayName": "grok-4-1-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": 0.39999999999999997, "above128kOutputUsdPer1MTokens": 1, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4-1-fast", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.3" ], "manual_model_modalities_note": "xAI Grok 4 family exact ids from official docs" }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4-1-fast-reasoning", "slug": "xai-xai-grok-4-1-fast-reasoning", "provider": "xai", "providerSlug": "xai", "name": "grok-4-1-fast-reasoning", "displayName": "grok-4-1-fast-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": 0.39999999999999997, "above128kOutputUsdPer1MTokens": 1, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-05-15", "shutdownDate": "2026-05-15", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "source": { "type": "litellm", "litellmKey": "xai/grok-4-1-fast-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.3" ], "manual_model_modalities_note": "xAI Grok 4 family exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4-1-fast-reasoning-latest", "slug": "xai-xai-grok-4-1-fast-reasoning-latest", "provider": "xai", "providerSlug": "xai", "name": "grok-4-1-fast-reasoning-latest", "displayName": "grok-4-1-fast-reasoning-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": 0.39999999999999997, "above128kOutputUsdPer1MTokens": 1, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4-1-fast-reasoning-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.3" ], "manual_model_modalities_note": "xAI Grok 4 family exact ids from official docs" }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4-1-fast-non-reasoning", "slug": "xai-xai-grok-4-1-fast-non-reasoning", "provider": "xai", "providerSlug": "xai", "name": "grok-4-1-fast-non-reasoning", "displayName": "grok-4-1-fast-non-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": 0.39999999999999997, "above128kOutputUsdPer1MTokens": 1, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-05-15", "shutdownDate": "2026-05-15", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "source": { "type": "litellm", "litellmKey": "xai/grok-4-1-fast-non-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.3" ], "manual_model_modalities_note": "xAI Grok 4 family exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4-1-fast-non-reasoning-latest", "slug": "xai-xai-grok-4-1-fast-non-reasoning-latest", "provider": "xai", "providerSlug": "xai", "name": "grok-4-1-fast-non-reasoning-latest", "displayName": "grok-4-1-fast-non-reasoning-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": 0.049999999999999996, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": 0.39999999999999997, "above128kOutputUsdPer1MTokens": 1, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "prompt_caching": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4-1-fast-non-reasoning-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning" }, "rawLitellm": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_above_128k_tokens": 4e-7, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 5e-7, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.3" ], "manual_model_modalities_note": "xAI Grok 4 family exact ids from official docs" }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4.20-multi-agent-beta-0309", "slug": "xai-xai-grok-4-20-multi-agent-beta-0309", "provider": "xai", "providerSlug": "xai", "name": "grok-4.20-multi-agent-beta-0309", "displayName": "grok-4.20-multi-agent-beta-0309", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4.20-multi-agent-beta-0309", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.20-multi-agent-beta-0309" ], "manual_model_modalities_note": "xAI Grok 4.20 multi-agent exact id from official docs" }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4.20-beta-0309-reasoning", "slug": "xai-xai-grok-4-20-beta-0309-reasoning", "provider": "xai", "providerSlug": "xai", "name": "grok-4.20-beta-0309-reasoning", "displayName": "grok-4.20-beta-0309-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4.20-beta-0309-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.20-0309-reasoning" ], "manual_model_modalities_note": "xAI Grok 4.20 reasoning exact ids from official docs" }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4.20-0309-reasoning", "slug": "xai-xai-grok-4-20-0309-reasoning", "provider": "xai", "providerSlug": "xai", "name": "grok-4.20-0309-reasoning", "displayName": "grok-4.20-0309-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4.20-0309-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.20-0309-reasoning" ], "manual_model_modalities_note": "xAI Grok 4.20 reasoning exact ids from official docs" }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4.20-beta-0309-non-reasoning", "slug": "xai-xai-grok-4-20-beta-0309-non-reasoning", "provider": "xai", "providerSlug": "xai", "name": "grok-4.20-beta-0309-non-reasoning", "displayName": "grok-4.20-beta-0309-non-reasoning", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 2000000, "maxInputTokens": 2000000, "maxOutputTokens": 2000000, "maxTokens": 2000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4.20-beta-0309-non-reasoning", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "litellm_provider": "xai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-4.20-0309-non-reasoning" ], "manual_model_modalities_note": "xAI Grok 4.20 non-reasoning exact ids from official docs" }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4.3", "slug": "xai-xai-grok-4-3", "provider": "xai", "providerSlug": "xai", "name": "grok-4.3", "displayName": "grok-4.3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 2.5, "above200kOutputUsdPer1MTokens": 5, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005 } }, "limits": { "contextWindow": 1000000, "maxInputTokens": 1000000, "maxOutputTokens": 1000000, "maxTokens": 1000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4.3", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-4.3-latest", "slug": "xai-xai-grok-4-3-latest", "provider": "xai", "providerSlug": "xai", "name": "grok-4.3-latest", "displayName": "grok-4.3-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 2.5, "above200kOutputUsdPer1MTokens": 5, "above200kCachedInputUsdPer1MTokens": 0.39999999999999997, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005 } }, "limits": { "contextWindow": 1000000, "maxInputTokens": 1000000, "maxOutputTokens": 1000000, "maxTokens": 1000000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-4.3-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "benchmarks": { "arcagiv2_accuracy_grok4_officiallaunchpost_114": { "label": "ARC-AGI-2", "category": "reasoning", "score": 15.9, "scoreText": "15.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article states this as the closed-model result on ARC-AGI V2 for Grok 4." }, "vendingbench_networth_grok4_officiallaunchpost_115": { "label": "Vending-Bench", "category": "agentic", "score": 4694.15, "scoreText": "$4694.15 net worth", "metric": "net worth", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; the article also reports 4569 units sold over 5 runs." }, "humanityslastexam_accuracy_grok4heavy_officiallaunchpost_116": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 50.7, "scoreText": "50.7% (text-only subset)", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy, text-only subset." }, "usamo25_accuracy_grok4heavy_officiallaunchpost_117": { "label": "USAMO'25", "category": "math", "score": 61.9, "scoreText": "61.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://x.ai/news/grok-4", "checked_at": "2026-05-31", "baseModelFamily": "grok-4", "exactModelOrSnapshot": "Grok 4 Heavy", "modelDeveloper": "xAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official xAI post; this result is reported for Grok 4 Heavy." } } }, { "id": "xai/xai/grok-beta", "slug": "xai-xai-grok-beta", "provider": "xai", "providerSlug": "xai", "name": "grok-beta", "displayName": "grok-beta", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-beta", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.000005, "litellm_provider": "xai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true } }, { "id": "xai/xai/grok-code-fast", "slug": "xai-xai-grok-code-fast", "provider": "xai", "providerSlug": "xai", "name": "grok-code-fast", "displayName": "grok-code-fast", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-8, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-code-fast", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-8, "input_cost_per_token": 2e-7, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-code-fast-1" ], "manual_model_modalities_note": "xAI Grok Code Fast exact ids from official docs" } }, { "id": "xai/xai/grok-code-fast-1", "slug": "xai-xai-grok-code-fast-1", "provider": "xai", "providerSlug": "xai", "name": "grok-code-fast-1", "displayName": "grok-code-fast-1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-8, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": "2026-05-15", "shutdownDate": "2026-05-15", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "checkedAt": "2026-05-31", "reviewStatus": "reviewed_official_docs_exact_model", "note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." }, "source": { "type": "litellm", "litellmKey": "xai/grok-code-fast-1", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-8, "input_cost_per_token": 2e-7, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-code-fast-1" ], "manual_model_modalities_note": "xAI Grok Code Fast exact ids from official docs", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.x.ai/developers/migration/may-15-retirement" ], "manual_model_lifecycle_checked_at": "2026-05-31", "manual_model_lifecycle_note": "xAI retirement notice says requests redirect to grok-4.3 after the retirement time." } }, { "id": "xai/xai/grok-code-fast-1-0825", "slug": "xai-xai-grok-code-fast-1-0825", "provider": "xai", "providerSlug": "xai", "name": "grok-code-fast-1-0825", "displayName": "grok-code-fast-1-0825", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 2e-8, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-code-fast-1-0825", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.x.ai/docs/models" }, "rawLitellm": { "cache_read_input_token_cost": 2e-8, "input_cost_per_token": 2e-7, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.0000015, "source": "https://docs.x.ai/docs/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.x.ai/developers/models/grok-code-fast-1" ], "manual_model_modalities_note": "xAI Grok Code Fast exact ids from official docs" } }, { "id": "xai/xai/grok-vision-beta", "slug": "xai-xai-grok-vision-beta", "provider": "xai", "providerSlug": "xai", "name": "grok-vision-beta", "displayName": "grok-vision-beta", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 5, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "xai/grok-vision-beta", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_image": 0.000005, "input_cost_per_token": 0.000005, "litellm_provider": "xai", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true } }, { "id": "bedrock_converse/zai.glm-4.7", "slug": "bedrock_converse-zai-glm-4-7", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "zai.glm-4.7", "displayName": "zai.glm-4.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai.glm-4.7", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000022, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "bedrock_converse/zai.glm-5", "slug": "bedrock_converse-zai-glm-5", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "zai.glm-5", "displayName": "zai.glm-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3.1999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai.glm-5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "benchmarks": { "hle_score_glm5_officialmodelcard_165": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 30.5, "scoreText": "30.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "gpqadiamond_score_glm5_officialmodelcard_166": { "label": "GPQA Diamond", "category": "reasoning", "score": 86, "scoreText": "86.0", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchverified_score_glm5_officialmodelcard_167": { "label": "SWE-bench Verified", "category": "coding", "score": 77.8, "scoreText": "77.8", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "bedrock_converse/zai.glm-4.7-flash", "slug": "bedrock_converse-zai-glm-4-7-flash", "provider": "bedrock_converse", "providerSlug": "bedrock_converse", "name": "zai.glm-4.7-flash", "displayName": "zai.glm-4.7-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai.glm-4.7-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 7e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-7, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "zai/zai/glm-5", "slug": "zai-zai-glm-5", "provider": "zai", "providerSlug": "zai", "name": "glm-5", "displayName": "glm-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3.1999999999999997, "cachedInputUsdPer1MTokens": 0.19999999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032 } }, "limits": { "contextWindow": null, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-5", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "hle_score_glm5_officialmodelcard_165": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 30.5, "scoreText": "30.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "gpqadiamond_score_glm5_officialmodelcard_166": { "label": "GPQA Diamond", "category": "reasoning", "score": 86, "scoreText": "86.0", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchverified_score_glm5_officialmodelcard_167": { "label": "SWE-bench Verified", "category": "coding", "score": 77.8, "scoreText": "77.8", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "zai/zai/glm-5-code", "slug": "zai-zai-glm-5-code", "provider": "zai", "providerSlug": "zai", "name": "glm-5-code", "displayName": "glm-5-code", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": null, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-5-code", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000005, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "hle_score_glm5_officialmodelcard_165": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 30.5, "scoreText": "30.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "gpqadiamond_score_glm5_officialmodelcard_166": { "label": "GPQA Diamond", "category": "reasoning", "score": 86, "scoreText": "86.0", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchverified_score_glm5_officialmodelcard_167": { "label": "SWE-bench Verified", "category": "coding", "score": 77.8, "scoreText": "77.8", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "zai/zai/glm-4.7", "slug": "zai-zai-glm-4-7", "provider": "zai", "providerSlug": "zai", "name": "glm-4.7", "displayName": "glm-4.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": null, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-4.7", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "zai/zai/glm-4.6", "slug": "zai-zai-glm-4-6", "provider": "zai", "providerSlug": "zai", "name": "glm-4.6", "displayName": "glm-4.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": null, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "prompt_caching": true, "reasoning": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-4.6", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_zaiglm46_benchmarkleaderboard_282": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_zaiglm46_benchmarkleaderboard_283": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_zaiglm46_benchmarkleaderboard_284": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_zaiglm46_benchmarkleaderboard_285": { "label": "GPQA Diamond", "category": "reasoning", "score": 78, "scoreText": "78.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_artificialanalysisintelligenceindex_score_zaiglm46_benchmarkleaderboard_310": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysiscodingindex_score_zaiglm46_benchmarkleaderboard_311": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysisagenticindex_score_zaiglm46_benchmarkleaderboard_312": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." } } }, { "id": "zai/zai/glm-4.5", "slug": "zai-zai-glm-4-5", "provider": "zai", "providerSlug": "zai", "name": "glm-4.5", "displayName": "glm-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": null, "maxInputTokens": 128000, "maxOutputTokens": 32000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-4.5", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "zai/zai/glm-4.5v", "slug": "zai-zai-glm-4-5v", "provider": "zai", "providerSlug": "zai", "name": "glm-4.5v", "displayName": "glm-4.5v", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018 } }, "limits": { "contextWindow": null, "maxInputTokens": 128000, "maxOutputTokens": 32000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-4.5v", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "zai/zai/glm-4.5-x", "slug": "zai-zai-glm-4-5-x", "provider": "zai", "providerSlug": "zai", "name": "glm-4.5-x", "displayName": "glm-4.5-x", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.2, "outputUsdPer1MTokens": 8.9, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000089 } }, "limits": { "contextWindow": null, "maxInputTokens": 128000, "maxOutputTokens": 32000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-4.5-x", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000089, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "zai/zai/glm-4.5-air", "slug": "zai-zai-glm-4-5-air", "provider": "zai", "providerSlug": "zai", "name": "glm-4.5-air", "displayName": "glm-4.5-air", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1.1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000011 } }, "limits": { "contextWindow": null, "maxInputTokens": 128000, "maxOutputTokens": 32000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-4.5-air", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000011, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "zai/zai/glm-4.5-airx", "slug": "zai-zai-glm-4-5-airx", "provider": "zai", "providerSlug": "zai", "name": "glm-4.5-airx", "displayName": "glm-4.5-airx", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.1, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000045 } }, "limits": { "contextWindow": null, "maxInputTokens": 128000, "maxOutputTokens": 32000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-4.5-airx", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000045, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "zai/zai/glm-4-32b-0414-128k", "slug": "zai-zai-glm-4-32b-0414-128k", "provider": "zai", "providerSlug": "zai", "name": "glm-4-32b-0414-128k", "displayName": "glm-4-32b-0414-128k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": 128000, "maxOutputTokens": 32000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-4-32b-0414-128k", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "zai/zai/glm-4.5-flash", "slug": "zai-zai-glm-4-5-flash", "provider": "zai", "providerSlug": "zai", "name": "glm-4.5-flash", "displayName": "glm-4.5-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": 128000, "maxOutputTokens": 32000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "zai/glm-4.5-flash", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.z.ai/guides/overview/pricing" }, "rawLitellm": { "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "vertex_ai/vertex_ai/search_api", "slug": "vertex_ai-vertex_ai-search_api", "provider": "Vertex AI", "providerSlug": "vertex_ai", "name": "search_api", "displayName": "search_api", "mode": "vector_store", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": 1.5, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0.0015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/search_api", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_query": 0.0015, "litellm_provider": "vertex_ai", "mode": "vector_store" } }, { "id": "openai/openai/container", "slug": "openai-openai-container", "provider": "OpenAI", "providerSlug": "openai", "name": "container", "displayName": "container", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": 0.03, "rawPricing": { "code_interpreter_cost_per_session": 0.03 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openai/container", "syncedAt": "2026-05-28" }, "rawLitellm": { "code_interpreter_cost_per_session": 0.03, "litellm_provider": "openai", "mode": "chat" } }, { "id": "openai/openai/sora-2", "slug": "openai-openai-sora-2", "provider": "OpenAI", "providerSlug": "openai", "name": "sora-2", "displayName": "sora-2", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.1 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openai/sora-2", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.openai.com/docs/api-reference/videos" }, "rawLitellm": { "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "720x1280", "1280x720" ] } }, { "id": "openai/openai/sora-2-pro", "slug": "openai-openai-sora-2-pro", "provider": "OpenAI", "providerSlug": "openai", "name": "sora-2-pro", "displayName": "sora-2-pro", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.3 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openai/sora-2-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.openai.com/docs/api-reference/videos" }, "rawLitellm": { "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "720x1280", "1280x720" ] } }, { "id": "openai/openai/sora-2-pro-high-res", "slug": "openai-openai-sora-2-pro-high-res", "provider": "OpenAI", "providerSlug": "openai", "name": "sora-2-pro-high-res", "displayName": "sora-2-pro-high-res", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.5 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "openai/sora-2-pro-high-res", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.openai.com/docs/api-reference/videos" }, "rawLitellm": { "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "1024x1792", "1792x1024" ] } }, { "id": "azure/azure/sora-2", "slug": "azure-azure-sora-2", "provider": "Azure", "providerSlug": "azure", "name": "sora-2", "displayName": "sora-2", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.1 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/sora-2", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/products/ai-services/video-generation" }, "rawLitellm": { "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "720x1280", "1280x720" ] } }, { "id": "azure/azure/sora-2-pro", "slug": "azure-azure-sora-2-pro", "provider": "Azure", "providerSlug": "azure", "name": "sora-2-pro", "displayName": "sora-2-pro", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.3 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/sora-2-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/products/ai-services/video-generation" }, "rawLitellm": { "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "720x1280", "1280x720" ] } }, { "id": "azure/azure/sora-2-pro-high-res", "slug": "azure-azure-sora-2-pro-high-res", "provider": "Azure", "providerSlug": "azure", "name": "sora-2-pro-high-res", "displayName": "sora-2-pro-high-res", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.5 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "azure/sora-2-pro-high-res", "syncedAt": "2026-05-28", "sourceUrl": "https://azure.microsoft.com/en-us/products/ai-services/video-generation" }, "rawLitellm": { "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "1024x1792", "1792x1024" ] } }, { "id": "runwayml/runwayml/gen4_turbo", "slug": "runwayml-runwayml-gen4_turbo", "provider": "runwayml", "providerSlug": "runwayml", "name": "gen4_turbo", "displayName": "gen4_turbo", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.05 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "runwayml/gen4_turbo", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.dev.runwayml.com/guides/pricing/" }, "rawLitellm": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_video_per_second": 0.05, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "1280x720", "720x1280" ], "metadata": { "comment": "5 credits per second @ $0.01 per credit = $0.05 per second" } } }, { "id": "runwayml/runwayml/gen4_aleph", "slug": "runwayml-runwayml-gen4_aleph", "provider": "runwayml", "providerSlug": "runwayml", "name": "gen4_aleph", "displayName": "gen4_aleph", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.15 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "runwayml/gen4_aleph", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.dev.runwayml.com/guides/pricing/" }, "rawLitellm": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_video_per_second": 0.15, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "1280x720", "720x1280" ], "metadata": { "comment": "15 credits per second @ $0.01 per credit = $0.15 per second" } } }, { "id": "runwayml/runwayml/gen3a_turbo", "slug": "runwayml-runwayml-gen3a_turbo", "provider": "runwayml", "providerSlug": "runwayml", "name": "gen3a_turbo", "displayName": "gen3a_turbo", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.05 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "runwayml/gen3a_turbo", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.dev.runwayml.com/guides/pricing/" }, "rawLitellm": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_video_per_second": 0.05, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "1280x720", "720x1280" ], "metadata": { "comment": "5 credits per second @ $0.01 per credit = $0.05 per second" } } }, { "id": "runwayml/runwayml/gen4_image", "slug": "runwayml-runwayml-gen4_image", "provider": "runwayml", "providerSlug": "runwayml", "name": "gen4_image", "displayName": "gen4_image", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 50000, "imageOutputUsdPer1MUnits": 50000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.05, "output_cost_per_image": 0.05 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "image" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "runwayml/gen4_image", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.dev.runwayml.com/guides/pricing/" }, "rawLitellm": { "litellm_provider": "runwayml", "mode": "image_generation", "input_cost_per_image": 0.05, "output_cost_per_image": 0.05, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ], "supported_resolutions": [ "1280x720", "1920x1080" ], "metadata": { "comment": "5 credits per 720p image or 8 credits per 1080p image @ $0.01 per credit. Using 5 credits ($0.05) as base cost" } } }, { "id": "runwayml/runwayml/gen4_image_turbo", "slug": "runwayml-runwayml-gen4_image_turbo", "provider": "runwayml", "providerSlug": "runwayml", "name": "gen4_image_turbo", "displayName": "gen4_image_turbo", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": 20000, "imageOutputUsdPer1MUnits": 20000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_image": 0.02, "output_cost_per_image": 0.02 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "image" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "runwayml/gen4_image_turbo", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.dev.runwayml.com/guides/pricing/" }, "rawLitellm": { "litellm_provider": "runwayml", "mode": "image_generation", "input_cost_per_image": 0.02, "output_cost_per_image": 0.02, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ], "supported_resolutions": [ "1280x720", "1920x1080" ], "metadata": { "comment": "2 credits per image (any resolution) @ $0.01 per credit = $0.02 per image" } } }, { "id": "runwayml/runwayml/eleven_multilingual_v2", "slug": "runwayml-runwayml-eleven_multilingual_v2", "provider": "runwayml", "providerSlug": "runwayml", "name": "eleven_multilingual_v2", "displayName": "eleven_multilingual_v2", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 3e-7, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 3e-7 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "runwayml/eleven_multilingual_v2", "syncedAt": "2026-05-28", "sourceUrl": "https://docs.dev.runwayml.com/guides/pricing/" }, "rawLitellm": { "litellm_provider": "runwayml", "mode": "audio_speech", "input_cost_per_character": 3e-7, "source": "https://docs.dev.runwayml.com/guides/pricing/", "metadata": { "comment": "Estimated cost based on standard TTS pricing. RunwayML uses ElevenLabs models." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-coder-480b-a35b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-coder-480b-a35b-instruct", "displayName": "qwen3-coder-480b-a35b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.44999999999999996, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.44999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.0000018 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.0000018, "litellm_provider": "fireworks_ai", "mode": "chat", "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-coder-480b-a35b-instruct", "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct" ], "manual_model_modalities_note": "Fireworks marks image input unsupported; the official Hugging Face card classifies the model as text-generation." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/flux-kontext-pro", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-flux-kontext-pro", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "flux-kontext-pro", "displayName": "flux-kontext-pro", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.04, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/flux-kontext-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8, "litellm_provider": "fireworks_ai", "mode": "image_generation" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/SSD-1B", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-ssd-1b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "SSD-1B", "displayName": "SSD-1B", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.00013, "outputUsdPer1MTokens": 0.00013, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.00013, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/SSD-1B", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-chronos-hermes-13b-v2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "chronos-hermes-13b-v2", "displayName": "chronos-hermes-13b-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/chronos-hermes-13b-v2" ], "manual_model_modalities_note": "Official model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-13b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-13b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-13b", "displayName": "code-llama-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-13b" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-13b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-13b-instruct", "displayName": "code-llama-13b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-13b-instruct" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-13b-python", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-13b-python", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-13b-python", "displayName": "code-llama-13b-python", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-13b-python", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-13b-python", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported, and Fireworks Text Models docs classify it as a text model." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-34b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-34b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-34b", "displayName": "code-llama-34b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-34b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-34b", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported, and Fireworks Text Models docs classify it as a text model." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-34b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-34b-instruct", "displayName": "code-llama-34b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-34b-instruct", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported, and Fireworks Text Models docs classify it as a text model." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-34b-python", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-34b-python", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-34b-python", "displayName": "code-llama-34b-python", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-34b-python", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-34b-python", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported, and Fireworks Text Models docs classify it as a text model." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-70b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-70b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-70b", "displayName": "code-llama-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-70b", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported, and Fireworks Text Models docs classify it as a text model." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-70b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-70b-instruct", "displayName": "code-llama-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-70b-instruct", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported, and Fireworks Text Models docs classify it as a text model." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-70b-python", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-70b-python", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-70b-python", "displayName": "code-llama-70b-python", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-70b-python", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-70b-python", "https://huggingface.co/codellama/CodeLlama-70b-Python-hf" ], "manual_model_modalities_note": "Fireworks lists this as Code Llama 70B Python, and the upstream HF card is text-generation only." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-7b", "displayName": "code-llama-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-7b", "https://huggingface.co/codellama/CodeLlama-7b-hf" ], "manual_model_modalities_note": "Fireworks model page and the upstream HF card both describe this as a text-generation code model." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-7b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-7b-instruct", "displayName": "code-llama-7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-7b-instruct", "https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf" ], "manual_model_modalities_note": "Fireworks model page and the upstream HF card both describe this as a text-generation code model." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-llama-7b-python", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-llama-7b-python", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-llama-7b-python", "displayName": "code-llama-7b-python", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-llama-7b-python", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-llama-7b-python", "https://huggingface.co/codellama/CodeLlama-7b-Python-hf" ], "manual_model_modalities_note": "Fireworks model page and the upstream HF card both describe this as a text-generation code model." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-code-qwen-1p5-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "code-qwen-1p5-7b", "displayName": "code-qwen-1p5-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/code-qwen-1p5-7b", "https://huggingface.co/Qwen/CodeQwen1.5-7B" ], "manual_model_modalities_note": "Fireworks model page and the upstream HF card both identify this as a text-generation code model." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/codegemma-2b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-codegemma-2b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "codegemma-2b", "displayName": "codegemma-2b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/codegemma-2b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/codegemma-2b", "https://huggingface.co/google/codegemma-2b" ], "manual_model_modalities_note": "CodeGemma 2B is documented as text-to-text and text-to-code on the upstream HF card, and Fireworks marks image input unsupported." }, "benchmarks": { "mmlu_5shottop1_gemma2pt27b_officialmodelcard_189": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "hellaswag_10shot_gemma2pt27b_officialmodelcard_190": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "humaneval_pass1_gemma2pt27b_officialmodelcard_191": { "label": "HumanEval", "category": "coding", "score": 51.8, "scoreText": "51.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "gsm8k_5shotmaj1_gemma2pt27b_officialmodelcard_192": { "label": "GSM8K", "category": "math", "score": 74, "scoreText": "74.0", "metric": "5-shot, maj@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "local_humanevalpython_score_codegemma2b_benchmarkleaderboard_43": { "label": "HumanEval", "category": "coding", "score": 27.28, "scoreText": "27.28", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-2B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the humaneval-python column for CodeGemma-2B." }, "local_javascript_score_codegemma2b_benchmarkleaderboard_44": { "label": "javascript", "category": "coding", "score": 29.94, "scoreText": "29.94", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-2B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the javascript column for CodeGemma-2B." }, "local_humanevalpython_score_codegemma7b_benchmarkleaderboard_45": { "label": "HumanEval", "category": "coding", "score": 40.13, "scoreText": "40.13", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the humaneval-python column for CodeGemma-7B." }, "local_javascript_score_codegemma7b_benchmarkleaderboard_46": { "label": "javascript", "category": "coding", "score": 43.06, "scoreText": "43.06", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the javascript column for CodeGemma-7B." }, "local_humanevalpython_score_codegemma7bit_benchmarkleaderboard_47": { "label": "HumanEval", "category": "coding", "score": 52.74, "scoreText": "52.74", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B-it", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the humaneval-python column for CodeGemma-7B-it." }, "local_javascript_score_codegemma7bit_benchmarkleaderboard_48": { "label": "javascript", "category": "coding", "score": 47.71, "scoreText": "47.71", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B-it", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the javascript column for CodeGemma-7B-it." }, "local_cpp_score_codegemma7bit_benchmarkleaderboard_49": { "label": "cpp", "category": "coding", "score": 42.6, "scoreText": "42.60", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B-it", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the cpp column for CodeGemma-7B-it." }, "local_mmlu_5shottop1_gemmapt27b_officialmodelcard_23": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_hellaswag_10shot_gemmapt27b_officialmodelcard_24": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_arcc_25shot_gemmapt27b_officialmodelcard_25": { "label": "ARC-Challenge", "category": "reasoning", "score": 71.4, "scoreText": "71.4", "metric": "25-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_triviaqa_5shot_gemmapt27b_officialmodelcard_26": { "label": "TriviaQA", "category": "general_knowledge", "score": 83.7, "scoreText": "83.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_realtoxicity_average_gemma2it27b_officialmodelcard_27": { "label": "RealToxicity", "category": "safety", "score": 8.84, "scoreText": "8.84", "metric": "average", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." }, "local_truthfulqa_score_gemma2it27b_officialmodelcard_28": { "label": "TruthfulQA", "category": "safety", "score": 51.6, "scoreText": "51.60", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/codegemma-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-codegemma-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "codegemma-7b", "displayName": "codegemma-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/codegemma-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/codegemma-7b" ], "manual_model_modalities_note": "Official model page says image input is not supported and describes text-to-text/text-to-code behavior." }, "benchmarks": { "local_humanevalpython_score_codegemma2b_benchmarkleaderboard_43": { "label": "HumanEval", "category": "coding", "score": 27.28, "scoreText": "27.28", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-2B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the humaneval-python column for CodeGemma-2B." }, "local_javascript_score_codegemma2b_benchmarkleaderboard_44": { "label": "javascript", "category": "coding", "score": 29.94, "scoreText": "29.94", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-2B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the javascript column for CodeGemma-2B." }, "local_humanevalpython_score_codegemma7b_benchmarkleaderboard_45": { "label": "HumanEval", "category": "coding", "score": 40.13, "scoreText": "40.13", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the humaneval-python column for CodeGemma-7B." }, "local_javascript_score_codegemma7b_benchmarkleaderboard_46": { "label": "javascript", "category": "coding", "score": 43.06, "scoreText": "43.06", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the javascript column for CodeGemma-7B." }, "local_humanevalpython_score_codegemma7bit_benchmarkleaderboard_47": { "label": "HumanEval", "category": "coding", "score": 52.74, "scoreText": "52.74", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B-it", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the humaneval-python column for CodeGemma-7B-it." }, "local_javascript_score_codegemma7bit_benchmarkleaderboard_48": { "label": "javascript", "category": "coding", "score": 47.71, "scoreText": "47.71", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B-it", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the javascript column for CodeGemma-7B-it." }, "local_cpp_score_codegemma7bit_benchmarkleaderboard_49": { "label": "cpp", "category": "coding", "score": 42.6, "scoreText": "42.60", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard/commit/d2421324214abc485324c2c2a1f409fa12d17c25", "checked_at": "2026-05-31", "baseModelFamily": "CodeGemma", "exactModelOrSnapshot": "CodeGemma-7B-it", "modelDeveloper": "Google", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "BigCode Models Leaderboard commit d242132 adds CodeGemma rows; this score is from the cpp column for CodeGemma-7B-it." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-cogito-671b-v2-p1", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "cogito-671b-v2-p1", "displayName": "cogito-671b-v2-p1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/cogito/cogito-671b-v2-p1" ], "manual_model_modalities_note": "Official model page shows image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-cogito-v1-preview-llama-3b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "cogito-v1-preview-llama-3b", "displayName": "cogito-v1-preview-llama-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/cogito-v1-preview-llama-3b" ], "manual_model_modalities_note": "Official model page shows image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-cogito-v1-preview-llama-70b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "cogito-v1-preview-llama-70b", "displayName": "cogito-v1-preview-llama-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/cogito-v1-preview-llama-70b" ], "manual_model_modalities_note": "Official model page shows image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-cogito-v1-preview-llama-8b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "cogito-v1-preview-llama-8b", "displayName": "cogito-v1-preview-llama-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/cogito-v1-preview-llama-8b" ], "manual_model_modalities_note": "Official model page shows image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-cogito-v1-preview-qwen-14b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "cogito-v1-preview-qwen-14b", "displayName": "cogito-v1-preview-qwen-14b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/cogito-v1-preview-qwen-14b" ], "manual_model_modalities_note": "Official model page shows image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-cogito-v1-preview-qwen-32b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "cogito-v1-preview-qwen-32b", "displayName": "cogito-v1-preview-qwen-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/cogito-v1-preview-qwen-32b" ], "manual_model_modalities_note": "Official model page shows image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/flux-kontext-max", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-flux-kontext-max", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "flux-kontext-max", "displayName": "flux-kontext-max", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/flux-kontext-max", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 8e-8, "output_cost_per_token": 8e-8, "litellm_provider": "fireworks_ai", "mode": "image_generation" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/dbrx-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-dbrx-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "dbrx-instruct", "displayName": "dbrx-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/dbrx-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/dbrx-instruct" ], "manual_model_modalities_note": "Official model page describes this as a large language model and says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-coder-1b-base", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-coder-1b-base", "displayName": "deepseek-coder-1b-base", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-coder-1b-base" ], "manual_model_modalities_note": "Official model page describes this as a code language model and says image input is not supported." }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-coder-33b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-coder-33b-instruct", "displayName": "deepseek-coder-33b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-coder-33b-instruct" ], "manual_model_modalities_note": "Official model page describes this as a code language model and says image input is not supported." }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-coder-7b-base", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-coder-7b-base", "displayName": "deepseek-coder-7b-base", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-coder-7b-base" ], "manual_model_modalities_note": "Official model page describes this as a code language model and says image input is not supported." }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-coder-7b-base-v1p5", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-coder-7b-base-v1p5", "displayName": "deepseek-coder-7b-base-v1p5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-coder-7b-base-v1p5" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-coder-7b-instruct-v1p5", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-coder-7b-instruct-v1p5", "displayName": "deepseek-coder-7b-instruct-v1p5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-coder-7b-instruct-v1p5" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-coder-v2-lite-base", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-coder-v2-lite-base", "displayName": "deepseek-coder-v2-lite-base", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-coder-v2-lite-base", "https://fireworks.ai/models?modelTypes=LLM" ], "manual_model_modalities_note": "Fireworks model page lists image input as not supported." }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-coder-v2-lite-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-coder-v2-lite-instruct", "displayName": "deepseek-coder-v2-lite-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-coder-v2-lite-instruct", "https://fireworks.ai/models?modelTypes=LLM" ], "manual_model_modalities_note": "Fireworks model page lists image input as not supported." }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-prover-v2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-prover-v2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-prover-v2", "displayName": "deepseek-prover-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-prover-v2", "https://fireworks.ai/models?modelTypes=LLM" ], "manual_model_modalities_note": "Fireworks model page lists image input as not supported." }, "benchmarks": { "minif2ftest_passratio_deepseekproverv2671b_officialmodelcard_152": { "label": "MiniF2F-test", "category": "science", "score": 88.9, "scoreText": "88.9%", "metric": "Pass ratio", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-671B", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Prover-V2", "exactModelOrSnapshot": "DeepSeek-Prover-V2-671B", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; score is stated directly in prose." }, "putnambench_solvedproblems_deepseekproverv2671b_officialmodelcard_153": { "label": "PutnamBench", "category": "science", "score": null, "scoreText": "49 out of 658", "metric": "Solved problems", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-671B", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Prover-V2", "exactModelOrSnapshot": "DeepSeek-Prover-V2-671B", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; raw count is stated directly in prose and is not normalized." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-r1-0528-distill-qwen3-8b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-r1-0528-distill-qwen3-8b", "displayName": "deepseek-r1-0528-distill-qwen3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-r1-0528-distill-qwen3-8b", "https://fireworks.ai/models?modelTypes=LLM" ], "manual_model_modalities_note": "Fireworks model page lists image input as not supported." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-r1-distill-llama-70b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-r1-distill-llama-70b", "displayName": "deepseek-r1-distill-llama-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-r1-distill-llama-70b" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-r1-distill-llama-8b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-r1-distill-llama-8b", "displayName": "deepseek-r1-distill-llama-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-r1-distill-llama-8b" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-r1-distill-qwen-14b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-r1-distill-qwen-14b", "displayName": "deepseek-r1-distill-qwen-14b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-r1-distill-qwen-14b" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-r1-distill-qwen-1p5b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-r1-distill-qwen-1p5b", "displayName": "deepseek-r1-distill-qwen-1p5b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-r1-distill-qwen-1p5b" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-r1-distill-qwen-32b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-r1-distill-qwen-32b", "displayName": "deepseek-r1-distill-qwen-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-r1-distill-qwen-32b" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-r1-distill-qwen-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-r1-distill-qwen-7b", "displayName": "deepseek-r1-distill-qwen-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-r1-distill-qwen-7b" ], "manual_model_modalities_note": "Official model page says image input is not supported." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-v2-lite-chat", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-v2-lite-chat", "displayName": "deepseek-v2-lite-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-v2-lite-chat" ], "manual_model_modalities_note": "Official model page lists image input as not supported." }, "benchmarks": { "local_mmlu_accuracy_deepseekv2moe236b_officialmodelcard_76": { "label": "MMLU", "category": "general_knowledge", "score": 78.5, "scoreText": "78.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 (MoE-236B)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Standard benchmark table on the official V2 model card." }, "local_ceval_accuracy_deepseekv2moe236b_officialmodelcard_77": { "label": "C-Eval", "category": "general_knowledge", "score": 81.7, "scoreText": "81.7", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 (MoE-236B)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Standard benchmark table on the official V2 model card." }, "local_humaneval_pass1_deepseekv2moe236b_officialmodelcard_78": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 (MoE-236B)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Standard benchmark table on the official V2 model card." }, "local_gsm8k_accuracy_deepseekv2moe236b_officialmodelcard_79": { "label": "GSM8K", "category": "math", "score": 79.2, "scoreText": "79.2", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 (MoE-236B)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Standard benchmark table on the official V2 model card." }, "local_math_accuracy_deepseekv2moe236b_officialmodelcard_80": { "label": "MATH", "category": "math", "score": 43.6, "scoreText": "43.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 (MoE-236B)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Standard benchmark table on the official V2 model card." }, "local_livecodebench09010401_pass1_deepseekv2chatrl_officialmodelcard_81": { "label": "LiveCodeBench", "category": "coding", "score": 32.5, "scoreText": "32.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 Chat (RL)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Chat-model benchmark table on the official V2 card." }, "local_alignbench_score_deepseekv2chatrl_officialmodelcard_82": { "label": "AlignBench", "category": "preference", "score": 7.91, "scoreText": "7.91", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 Chat (RL)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Chinese open-ended generation table on the official V2 card." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/deepseek-v2p5", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-deepseek-v2p5", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "deepseek-v2p5", "displayName": "deepseek-v2p5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/deepseek-v2p5", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/deepseek-v2p5" ], "manual_model_modalities_note": "Official model page lists image input as not supported." }, "benchmarks": { "local_mmlu_accuracy_deepseekv2moe236b_officialmodelcard_76": { "label": "MMLU", "category": "general_knowledge", "score": 78.5, "scoreText": "78.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 (MoE-236B)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Standard benchmark table on the official V2 model card." }, "local_ceval_accuracy_deepseekv2moe236b_officialmodelcard_77": { "label": "C-Eval", "category": "general_knowledge", "score": 81.7, "scoreText": "81.7", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 (MoE-236B)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Standard benchmark table on the official V2 model card." }, "local_humaneval_pass1_deepseekv2moe236b_officialmodelcard_78": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 (MoE-236B)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Standard benchmark table on the official V2 model card." }, "local_gsm8k_accuracy_deepseekv2moe236b_officialmodelcard_79": { "label": "GSM8K", "category": "math", "score": 79.2, "scoreText": "79.2", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 (MoE-236B)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Standard benchmark table on the official V2 model card." }, "local_math_accuracy_deepseekv2moe236b_officialmodelcard_80": { "label": "MATH", "category": "math", "score": 43.6, "scoreText": "43.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 (MoE-236B)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Standard benchmark table on the official V2 model card." }, "local_livecodebench09010401_pass1_deepseekv2chatrl_officialmodelcard_81": { "label": "LiveCodeBench", "category": "coding", "score": 32.5, "scoreText": "32.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 Chat (RL)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Chat-model benchmark table on the official V2 card." }, "local_alignbench_score_deepseekv2chatrl_officialmodelcard_82": { "label": "AlignBench", "category": "preference", "score": 7.91, "scoreText": "7.91", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V2", "exactModelOrSnapshot": "DeepSeek-V2 Chat (RL)", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Chinese open-ended generation table on the official V2 card." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/devstral-small-2505", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-devstral-small-2505", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "devstral-small-2505", "displayName": "devstral-small-2505", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/devstral-small-2505", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/devstral-small-2505" ], "manual_model_modalities_note": "Official model page lists image input as not supported." }, "benchmarks": { "local_devstralswebenchverified_swebenchverified_devstralsmall2505_officiallaunchpost_158": { "label": "SWE-bench Verified", "category": "coding", "score": 46.8, "scoreText": "46.8%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2505", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post states Devstral achieves 46.8% on SWE-Bench Verified." }, "local_devstralupdateswebenchverified_swebenchverified_devstralsmall2507_officiallaunchpost_159": { "label": "SWE-bench Verified", "category": "coding", "score": 53.6, "scoreText": "53.6%", "metric": "SWE-Bench Verified", "higherIsBetter": true, "source_url": "https://mistral.ai/news/devstral-2507", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "devstral-small-2507", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official update post states Devstral Small 1.1 achieves 53.6% on SWE-Bench Verified." }, "local_swebenchverified_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_249": { "label": "SWE-bench Verified", "category": "agentic", "score": 68, "scoreText": "68.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchmultilingual_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_250": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 55.7, "scoreText": "55.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_terminalbench2_score_mistralaidevstralsmall224binstruct2512_officialmodelcard_251": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 22.5, "scoreText": "22.5%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "mistralai/Devstral-Small-2-24B-Instruct-2512", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official benchmark table on the HF card." }, "local_swebenchverified_score_devstral2_officialmodelcard_252": { "label": "SWE-bench Verified", "category": "agentic", "score": 72.2, "scoreText": "72.2%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_swebenchmultilingual_score_devstral2_officialmodelcard_253": { "label": "SWE-bench Multilingual", "category": "agentic", "score": 61.3, "scoreText": "61.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." }, "local_terminalbench2_score_devstral2_officialmodelcard_254": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 32.6, "scoreText": "32.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "checked_at": "2026-05-31", "baseModelFamily": "Devstral", "exactModelOrSnapshot": "Devstral 2", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Devstral Small 2 page includes a comparison table row for Devstral 2." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-dobby-mini-unhinged-plus-llama-3-1-8b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "dobby-mini-unhinged-plus-llama-3-1-8b", "displayName": "dobby-mini-unhinged-plus-llama-3-1-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/sentientfoundation-serverless/dobby-mini-unhinged-plus-llama-3-1-8b" ], "manual_model_modalities_note": "Official model page lists image input as not supported." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-dobby-unhinged-llama-3-3-70b-new", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "dobby-unhinged-llama-3-3-70b-new", "displayName": "dobby-unhinged-llama-3-3-70b-new", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/sentientfoundation/dobby-unhinged-llama-3-3-70b-new" ], "manual_model_modalities_note": "Official model page lists image input as not supported and no vision support." }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-dolphin-2-9-2-qwen2-72b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "dolphin-2-9-2-qwen2-72b", "displayName": "dolphin-2-9-2-qwen2-72b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/dolphin-2-9-2-qwen2-72b" ], "manual_model_modalities_note": "Official model page lists image input as not supported and no vision support." }, "benchmarks": { "mmlu_score_qwen272b_officialmodelcard_154": { "label": "MMLU", "category": "general_knowledge", "score": 84.2, "scoreText": "84.2", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-72B", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-72B", "exactModelOrSnapshot": "Qwen2-72B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "mmlupro_score_qwen272b_officialmodelcard_155": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 55.6, "scoreText": "55.6", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-72B", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-72B", "exactModelOrSnapshot": "Qwen2-72B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqa_score_qwen272b_officialmodelcard_156": { "label": "GPQA", "category": "reasoning", "score": 37.9, "scoreText": "37.9", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-72B", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-72B", "exactModelOrSnapshot": "Qwen2-72B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-dolphin-2p6-mixtral-8x7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "dolphin-2p6-mixtral-8x7b", "displayName": "dolphin-2p6-mixtral-8x7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/dolphin-2p6-mixtral-8x7b", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Official model page marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-ernie-4p5-21b-a3b-pt", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "ernie-4p5-21b-a3b-pt", "displayName": "ernie-4p5-21b-a3b-pt", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/ernie-4p5-21b-a3b-pt", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Official model page marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-ernie-4p5-300b-a47b-pt", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "ernie-4p5-300b-a47b-pt", "displayName": "ernie-4p5-300b-a47b-pt", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/ernie-4p5-300b-a47b-pt", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Official model page marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/fare-20b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-fare-20b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "fare-20b", "displayName": "fare-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/fare-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/fare-20b", "https://fireworks.ai/models?modelTypes=LLM", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Official model library lists it as an LLM and the model page marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/firefunction-v1", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-firefunction-v1", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "firefunction-v1", "displayName": "firefunction-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/firefunction-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/firefunction-v1", "https://fireworks.ai/models?modelTypes=LLM", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Official model library lists it as an LLM and the model page marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/firellava-13b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-firellava-13b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "firellava-13b", "displayName": "firellava-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/firellava-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/firellava-13b", "https://docs.fireworks.ai/guides/querying-vision-language-models" ], "manual_model_modalities_note": "Official model page marks image input as supported, and Fireworks vision docs say vision-language models process text and images in one request." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-firesearch-ocr-v6", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "firesearch-ocr-v6", "displayName": "firesearch-ocr-v6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/firesearch-ocr-v6", "https://docs.fireworks.ai/guides/querying-vision-language-models" ], "manual_model_modalities_note": "Fireworks model page marks image input supported, and Fireworks vision docs describe VLMs as processing text and images including OCR tasks." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/fireworks-asr-large", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-fireworks-asr-large", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "fireworks-asr-large", "displayName": "fireworks-asr-large", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/fireworks-asr-large", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "fireworks_ai", "mode": "audio_transcription", "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/fireworks-asr-v2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-fireworks-asr-v2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "fireworks-asr-v2", "displayName": "fireworks-asr-v2", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "fireworks_ai", "mode": "audio_transcription", "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/flux-1-dev", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-flux-1-dev", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "flux-1-dev", "displayName": "flux-1-dev", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/flux-1-dev", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-flux-1-dev-controlnet-union", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "flux-1-dev-controlnet-union", "displayName": "flux-1-dev-controlnet-union", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.001, "outputUsdPer1MTokens": 0.001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-9, "output_cost_per_token": 1e-9 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-9, "output_cost_per_token": 1e-9, "litellm_provider": "fireworks_ai", "mode": "chat" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-flux-1-dev-fp8", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "flux-1-dev-fp8", "displayName": "flux-1-dev-fp8", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.0005, "outputUsdPer1MTokens": 0.0005, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.0005, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-10, "output_cost_per_token": 5e-10 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 5e-10, "output_cost_per_token": 5e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/flux-1-schnell", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-flux-1-schnell", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "flux-1-schnell", "displayName": "flux-1-schnell", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/flux-1-schnell", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-flux-1-schnell-fp8", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "flux-1-schnell-fp8", "displayName": "flux-1-schnell-fp8", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.00035, "outputUsdPer1MTokens": 0.00035, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.00035, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-10, "output_cost_per_token": 3.5e-10 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 3.5e-10, "output_cost_per_token": 3.5e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/gemma-2b-it", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-gemma-2b-it", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "gemma-2b-it", "displayName": "gemma-2b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/gemma-2b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/gemma-2b-it" ], "manual_model_modalities_note": "Fireworks page describes Gemma as text-to-text and marks image input unsupported." }, "benchmarks": { "mmlu_5shottop1_gemma2pt27b_officialmodelcard_189": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "hellaswag_10shot_gemma2pt27b_officialmodelcard_190": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "humaneval_pass1_gemma2pt27b_officialmodelcard_191": { "label": "HumanEval", "category": "coding", "score": 51.8, "scoreText": "51.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "gsm8k_5shotmaj1_gemma2pt27b_officialmodelcard_192": { "label": "GSM8K", "category": "math", "score": 74, "scoreText": "74.0", "metric": "5-shot, maj@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "local_mmlu_5shottop1_gemmapt27b_officialmodelcard_23": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_hellaswag_10shot_gemmapt27b_officialmodelcard_24": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_arcc_25shot_gemmapt27b_officialmodelcard_25": { "label": "ARC-Challenge", "category": "reasoning", "score": 71.4, "scoreText": "71.4", "metric": "25-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_triviaqa_5shot_gemmapt27b_officialmodelcard_26": { "label": "TriviaQA", "category": "general_knowledge", "score": 83.7, "scoreText": "83.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_realtoxicity_average_gemma2it27b_officialmodelcard_27": { "label": "RealToxicity", "category": "safety", "score": 8.84, "scoreText": "8.84", "metric": "average", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." }, "local_truthfulqa_score_gemma2it27b_officialmodelcard_28": { "label": "TruthfulQA", "category": "safety", "score": 51.6, "scoreText": "51.60", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/gemma-3-27b-it", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-gemma-3-27b-it", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "gemma-3-27b-it", "displayName": "gemma-3-27b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/gemma-3-27b-it" ], "manual_model_modalities_note": "Fireworks page marks image input unsupported on Fireworks." }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/gemma-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-gemma-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "gemma-7b", "displayName": "gemma-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/gemma-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/gemma-7b" ], "manual_model_modalities_note": "Fireworks page describes Gemma as text-to-text and marks image input unsupported." }, "benchmarks": { "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/gemma-7b-it", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-gemma-7b-it", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "gemma-7b-it", "displayName": "gemma-7b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/gemma-7b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/gemma-7b-it" ], "manual_model_modalities_note": "Fireworks page describes Gemma as text-to-text and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/gemma2-9b-it", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-gemma2-9b-it", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "gemma2-9b-it", "displayName": "gemma2-9b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/gemma2-9b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/gemma2-9b-it" ], "manual_model_modalities_note": "Fireworks page describes Gemma as text-to-text and marks image input unsupported." }, "benchmarks": { "mmlu_5shottop1_gemma2pt27b_officialmodelcard_189": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "hellaswag_10shot_gemma2pt27b_officialmodelcard_190": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "humaneval_pass1_gemma2pt27b_officialmodelcard_191": { "label": "HumanEval", "category": "coding", "score": 51.8, "scoreText": "51.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "gsm8k_5shotmaj1_gemma2pt27b_officialmodelcard_192": { "label": "GSM8K", "category": "math", "score": 74, "scoreText": "74.0", "metric": "5-shot, maj@1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-2b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 2 model card; used the 27B column from the benchmark table." }, "local_mmlu_5shottop1_gemmapt27b_officialmodelcard_23": { "label": "MMLU", "category": "general_knowledge", "score": 75.2, "scoreText": "75.2", "metric": "5-shot, top-1", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_hellaswag_10shot_gemmapt27b_officialmodelcard_24": { "label": "HellaSwag", "category": "reasoning", "score": 86.4, "scoreText": "86.4", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_arcc_25shot_gemmapt27b_officialmodelcard_25": { "label": "ARC-Challenge", "category": "reasoning", "score": 71.4, "scoreText": "71.4", "metric": "25-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_triviaqa_5shot_gemmapt27b_officialmodelcard_26": { "label": "TriviaQA", "category": "general_knowledge", "score": 83.7, "scoreText": "83.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 benchmark results table on the 27B model card." }, "local_realtoxicity_average_gemma2it27b_officialmodelcard_27": { "label": "RealToxicity", "category": "safety", "score": 8.84, "scoreText": "8.84", "metric": "average", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." }, "local_truthfulqa_score_gemma2it27b_officialmodelcard_28": { "label": "TruthfulQA", "category": "safety", "score": 51.6, "scoreText": "51.60", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-2-27b", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 2", "exactModelOrSnapshot": "Gemma 2 IT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 2 safety table on the 27B model card." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/glm-4p5v", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-glm-4p5v", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "glm-4p5v", "displayName": "glm-4p5v", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/glm-4p5v", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "mode": "chat", "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/glm-4p5v" ], "manual_model_modalities_note": "Fireworks page describes this as a vision-language model with image and video understanding; output normalized to text only." }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-gpt-oss-safeguard-120b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "gpt-oss-safeguard-120b", "displayName": "gpt-oss-safeguard-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/gpt-oss-safeguard-120b" ], "manual_model_modalities_note": "Fireworks page describes this as a language model and marks image input unsupported." }, "benchmarks": { "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-gpt-oss-safeguard-20b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "gpt-oss-safeguard-20b", "displayName": "gpt-oss-safeguard-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/gpt-oss-safeguard-20b" ], "manual_model_modalities_note": "Fireworks page describes this as a language model and marks image input unsupported." }, "benchmarks": { "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-hermes-2-pro-mistral-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "hermes-2-pro-mistral-7b", "displayName": "hermes-2-pro-mistral-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/hermes-2-pro-mistral-7b" ], "manual_model_modalities_note": "Fireworks page describes this as a language model and marks image input unsupported." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/internvl3-38b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-internvl3-38b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "internvl3-38b", "displayName": "internvl3-38b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/internvl3-38b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/internvl3-38b" ], "manual_model_modalities_note": "Fireworks page marks image input supported and mentions video understanding; output normalized to text only." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/internvl3-78b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-internvl3-78b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "internvl3-78b", "displayName": "internvl3-78b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/internvl3-78b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/internvl3-78b" ], "manual_model_modalities_note": "Fireworks page marks image input supported and mentions video understanding; output normalized to text only." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/internvl3-8b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-internvl3-8b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "internvl3-8b", "displayName": "internvl3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/internvl3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/internvl3-8b", "https://huggingface.co/OpenGVLab/InternVL3-8B" ], "manual_model_modalities_note": "Fireworks marks image input supported, and the upstream HF card states interleaved image, video, and text inputs with text generation output." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-japanese-stable-diffusion-xl", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "japanese-stable-diffusion-xl", "displayName": "japanese-stable-diffusion-xl", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.00013, "outputUsdPer1MTokens": 0.00013, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.00013, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/kat-coder", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-kat-coder", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "kat-coder", "displayName": "kat-coder", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/kat-coder", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/kat-coder" ], "manual_model_modalities_note": "Fireworks page marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/kat-dev-32b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-kat-dev-32b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "kat-dev-32b", "displayName": "kat-dev-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/kat-dev-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/kat-dev-32b", "https://huggingface.co/Kwaipilot/KAT-Dev" ], "manual_model_modalities_note": "Fireworks page marks image input unsupported, and the upstream HF card is text-generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-kat-dev-72b-exp", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "kat-dev-72b-exp", "displayName": "kat-dev-72b-exp", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/kat-dev-72b-exp", "https://huggingface.co/Kwaipilot" ], "manual_model_modalities_note": "Fireworks page marks image input unsupported, and the upstream Kwaipilot listing is text-generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-guard-2-8b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-guard-2-8b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-guard-2-8b", "displayName": "llama-guard-2-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-guard-2-8b", "https://huggingface.co/meta-llama/Meta-Llama-Guard-2-8B" ], "manual_model_modalities_note": "Fireworks page says it generates text for safety classification and marks image input unsupported; upstream HF card is text-generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-guard-3-1b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-guard-3-1b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-guard-3-1b", "displayName": "llama-guard-3-1b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-guard-3-1b", "https://huggingface.co/meta-llama/Llama-Guard-3-1B" ], "manual_model_modalities_note": "Fireworks page says it generates text for safety classification and marks image input unsupported; upstream HF card is text-generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-guard-3-8b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-guard-3-8b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-guard-3-8b", "displayName": "llama-guard-3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-guard-3-8b" ], "manual_model_modalities_note": "Official page says it generates text and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v2-13b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v2-13b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v2-13b", "displayName": "llama-v2-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v2-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v2-13b" ], "manual_model_modalities_note": "Official page describes the model family as generative text models and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v2-13b-chat", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v2-13b-chat", "displayName": "llama-v2-13b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v2-13b-chat" ], "manual_model_modalities_note": "Official page describes this as a generative text model optimized for dialogue and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v2-70b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v2-70b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v2-70b", "displayName": "llama-v2-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v2-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v2-70b" ], "manual_model_modalities_note": "Official page describes the model family as generative text models and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v2-70b-chat", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v2-70b-chat", "displayName": "llama-v2-70b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v2-70b-chat" ], "manual_model_modalities_note": "Official page describes this as a generative text model optimized for dialogue and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v2-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v2-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v2-7b", "displayName": "llama-v2-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v2-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v2-7b" ], "manual_model_modalities_note": "Official page describes the model family as generative text models and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v2-7b-chat", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v2-7b-chat", "displayName": "llama-v2-7b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v2-7b-chat" ], "manual_model_modalities_note": "Fireworks page describes this as a generative text model and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3-70b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3-70b-instruct", "displayName": "llama-v3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3-70b-instruct" ], "manual_model_modalities_note": "Fireworks page describes this as a generative text model and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3-70b-instruct-hf", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3-70b-instruct-hf", "displayName": "llama-v3-70b-instruct-hf", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3-70b-instruct-hf" ], "manual_model_modalities_note": "Fireworks page describes this as a generative text model and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3-8b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3-8b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3-8b", "displayName": "llama-v3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3-8b" ], "manual_model_modalities_note": "Fireworks page describes this as a language model and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3-8b-instruct-hf", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3-8b-instruct-hf", "displayName": "llama-v3-8b-instruct-hf", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3-8b-instruct-hf" ], "manual_model_modalities_note": "Fireworks page describes this as a generative text model and marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p1-405b-instruct-long", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p1-405b-instruct-long", "displayName": "llama-v3p1-405b-instruct-long", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p1-405b-instruct-long" ], "manual_model_modalities_note": "Fireworks page explicitly says these are text-only models and marks image input unsupported." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p1-70b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p1-70b-instruct", "displayName": "llama-v3p1-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p1-70b-instruct" ], "manual_model_modalities_note": "Official Fireworks model page shows this model as text-only and lists image input not supported." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p1-70b-instruct-1b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p1-70b-instruct-1b", "displayName": "llama-v3p1-70b-instruct-1b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p1-70b-instruct-1b" ], "manual_model_modalities_note": "Official Fireworks model page lists image input not supported and describes the model family as text-only." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p1-nemotron-70b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p1-nemotron-70b-instruct", "displayName": "llama-v3p1-nemotron-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p1-nemotron-70b-instruct" ], "manual_model_modalities_note": "Official Fireworks model page lists image input not supported." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p2-1b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p2-1b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p2-1b", "displayName": "llama-v3p2-1b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p2-1b" ], "manual_model_modalities_note": "Official Fireworks model page states text in/text out and lists image input not supported." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p2-3b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p2-3b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p2-3b", "displayName": "llama-v3p2-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p2-3b" ], "manual_model_modalities_note": "Official Fireworks model page states text in/text out and lists image input not supported." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llama-v3p3-70b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llama-v3p3-70b-instruct", "displayName": "llama-v3p3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.fireworks.ai/updates/changelog" ], "checkedAt": "2026-06-02", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Fireworks changelog says serverless Llama 3.3 70B Instruct was removed on May 14, 2026; mapped to the exact Fireworks model slug by naming convention." }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llama-v3p3-70b-instruct" ], "manual_model_modalities_note": "Official Fireworks model page lists image input not supported.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.fireworks.ai/updates/changelog" ], "manual_model_lifecycle_checked_at": "2026-06-02", "manual_model_lifecycle_note": "Fireworks changelog says serverless Llama 3.3 70B Instruct was removed on May 14, 2026; mapped to the exact Fireworks model slug by naming convention." }, "benchmarks": { "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llamaguard-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llamaguard-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llamaguard-7b", "displayName": "llamaguard-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llamaguard-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llamaguard-7b", "https://huggingface.co/meta-llama/LlamaGuard-7b" ], "manual_model_modalities_note": "Fireworks marks image input unsupported; upstream HF card is text-generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/llava-yi-34b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-llava-yi-34b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "llava-yi-34b", "displayName": "llava-yi-34b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/llava-yi-34b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/llava-yi-34b" ], "manual_model_modalities_note": "Vision model; Fireworks marks image input supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/minimax-m1-80k", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-minimax-m1-80k", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "minimax-m1-80k", "displayName": "minimax-m1-80k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/minimax-m1-80k", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/minimax-m1-80k", "https://huggingface.co/MiniMaxAI/MiniMax-M1-80k" ], "manual_model_modalities_note": "Fireworks marks image input unsupported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/minimax-m2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-minimax-m2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "minimax-m2", "displayName": "minimax-m2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/minimax-m2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/minimax-m2", "https://huggingface.co/MiniMaxAI/MiniMax-M2" ], "manual_model_modalities_note": "Fireworks marks image input unsupported." }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-ministral-3-14b-instruct-2512", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "ministral-3-14b-instruct-2512", "displayName": "ministral-3-14b-instruct-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/ministral-3-14b-instruct-2512" ], "manual_model_modalities_note": "Fireworks page says the model has a vision encoder and image input is supported; output normalized to text." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-ministral-3-3b-instruct-2512", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "ministral-3-3b-instruct-2512", "displayName": "ministral-3-3b-instruct-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/ministral-3-3b-instruct-2512" ], "manual_model_modalities_note": "Fireworks page says the model has a vision encoder and image input is supported; output normalized to text." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-ministral-3-8b-instruct-2512", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "ministral-3-8b-instruct-2512", "displayName": "ministral-3-8b-instruct-2512", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/ministral-3-8b-instruct-2512" ], "manual_model_modalities_note": "Fireworks page says the model has vision capabilities and image input is supported; output normalized to text." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mistral-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mistral-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mistral-7b", "displayName": "mistral-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mistral-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mistral-7b" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mistral-7b-instruct-4k", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mistral-7b-instruct-4k", "displayName": "mistral-7b-instruct-4k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mistral-7b-instruct-4k" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mistral-7b-instruct-v0p2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mistral-7b-instruct-v0p2", "displayName": "mistral-7b-instruct-v0p2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mistral-7b-instruct-v0p2" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mistral-7b-instruct-v3", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mistral-7b-instruct-v3", "displayName": "mistral-7b-instruct-v3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mistral-7b-instruct-v3" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mistral-7b-v0p2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mistral-7b-v0p2", "displayName": "mistral-7b-v0p2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mistral-7b-v0p2" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mistral-large-3-fp8", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mistral-large-3-fp8", "displayName": "mistral-large-3-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 256000, "maxInputTokens": 256000, "maxOutputTokens": 256000, "maxTokens": 256000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mistral-large-3-fp8" ], "manual_model_modalities_note": "Fireworks model page says this model is multimodal and supports image input; output normalized to text." }, "benchmarks": { "mmlu_accuracy_mistrallarge3_benchmarkleaderboard_118": { "label": "MMLU", "category": "general_knowledge", "score": 85.5, "scoreText": "85.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "mmlupro_accuracy_mistrallarge3_benchmarkleaderboard_119": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 78, "scoreText": "78.0", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "gpqadiamond_accuracy_mistrallarge3_benchmarkleaderboard_120": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 43.9, "scoreText": "43.9", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "humaneval_pass1_mistrallarge3_benchmarkleaderboard_121": { "label": "HumanEval", "category": "coding", "score": 92, "scoreText": "92.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "math500_accuracy_mistrallarge3_benchmarkleaderboard_122": { "label": "MATH-500", "category": "math", "score": 93.6, "scoreText": "93.6", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "aime2024_accuracy_mistrallarge3_benchmarkleaderboard_123": { "label": "AIME 2024", "category": "math", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "aime2025_accuracy_mistrallarge3_benchmarkleaderboard_124": { "label": "AIME 2025", "category": "math", "score": 40, "scoreText": "40.0", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." }, "simpleqa_accuracy_mistrallarge3_benchmarkleaderboard_125": { "label": "SimpleQA", "category": "general_knowledge", "score": 23.8, "scoreText": "23.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://frontierbenchmarks.com/models/mistral-large-3/", "checked_at": "2026-05-31", "baseModelFamily": "mistral-large-3", "exactModelOrSnapshot": "Mistral Large 3", "modelDeveloper": "Mistral AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Atlas page for the model family; values are listed directly on the page." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mistral-nemo-base-2407", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mistral-nemo-base-2407", "displayName": "mistral-nemo-base-2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mistral-nemo-base-2407" ], "manual_model_modalities_note": "Fireworks page describes it as a pretrained generative text model and says image input is not supported." }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mistral-nemo-instruct-2407", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mistral-nemo-instruct-2407", "displayName": "mistral-nemo-instruct-2407", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mistral-nemo-instruct-2407" ], "manual_model_modalities_note": "Fireworks page says chat completions API is enabled and image input is not supported." }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mistral-small-24b-instruct-2501", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mistral-small-24b-instruct-2501", "displayName": "mistral-small-24b-instruct-2501", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mistral-small-24b-instruct-2501" ], "manual_model_modalities_note": "Fireworks page says image input is not supported and describes it as an instruction-tuned LLM." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mixtral-8x22b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mixtral-8x22b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mixtral-8x22b", "displayName": "mixtral-8x22b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mixtral-8x22b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mixtral-8x22b" ], "manual_model_modalities_note": "Fireworks page describes it as a pretrained generative sparse Mixture-of-Experts model and says image input is not supported." }, "benchmarks": { "gsm8kmaj8_8shot_mixtral8x22binstruct_officiallaunchpost_212": { "label": "GSM8K maj@8", "category": "math", "score": 90.8, "scoreText": "90.8%", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on GSM8K maj@8." }, "mathmaj4_4shot_mixtral8x22binstruct_officiallaunchpost_213": { "label": "Math maj@4", "category": "math", "score": 44.6, "scoreText": "44.6%", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on Math maj@4." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mixtral-8x22b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mixtral-8x22b-instruct", "displayName": "mixtral-8x22b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mixtral-8x22b-instruct" ], "manual_model_modalities_note": "Fireworks page says chat completions API is enabled and image input is not supported." }, "benchmarks": { "gsm8kmaj8_8shot_mixtral8x22binstruct_officiallaunchpost_212": { "label": "GSM8K maj@8", "category": "math", "score": 90.8, "scoreText": "90.8%", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on GSM8K maj@8." }, "mathmaj4_4shot_mixtral8x22binstruct_officiallaunchpost_213": { "label": "Math maj@4", "category": "math", "score": 44.6, "scoreText": "44.6%", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://mistral.ai/news/mixtral-8x22b?_hsmi=303113706", "checked_at": "2026-05-31", "baseModelFamily": "Mixtral 8x22B", "exactModelOrSnapshot": "Mixtral 8x22B Instruct", "modelDeveloper": "Mistral AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post explicitly states the instructed Mixtral 8x22B score on Math maj@4." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mixtral-8x7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mixtral-8x7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mixtral-8x7b", "displayName": "mixtral-8x7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mixtral-8x7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mixtral-8x7b" ], "manual_model_modalities_note": "Fireworks page describes it as a large language model and says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mixtral-8x7b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mixtral-8x7b-instruct", "displayName": "mixtral-8x7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mixtral-8x7b-instruct" ], "manual_model_modalities_note": "Fireworks page says no image input or multimodal support." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mixtral-8x7b-instruct-hf", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mixtral-8x7b-instruct-hf", "displayName": "mixtral-8x7b-instruct-hf", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mixtral-8x7b-instruct-hf" ], "manual_model_modalities_note": "Fireworks page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/mythomax-l2-13b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-mythomax-l2-13b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "mythomax-l2-13b", "displayName": "mythomax-l2-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/mythomax-l2-13b" ], "manual_model_modalities_note": "Fireworks page describes it as a language model and says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-nemotron-nano-v2-12b-vl", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "nemotron-nano-v2-12b-vl", "displayName": "nemotron-nano-v2-12b-vl", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/nemotron-nano-v2-12b-vl" ], "manual_model_modalities_note": "Fireworks page describes it as a multimodal reasoning model for text, images, and videos; output normalized to text." }, "benchmarks": { "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-nous-capybara-7b-v1p9", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "nous-capybara-7b-v1p9", "displayName": "nous-capybara-7b-v1p9", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/nous-capybara-7b-v1p9" ], "manual_model_modalities_note": "Fireworks page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-nous-hermes-2-mixtral-8x7b-dpo", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "nous-hermes-2-mixtral-8x7b-dpo", "displayName": "nous-hermes-2-mixtral-8x7b-dpo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/nous-hermes-2-mixtral-8x7b-dpo" ], "manual_model_modalities_note": "Fireworks page identifies this as a base LLM and says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-nous-hermes-2-yi-34b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "nous-hermes-2-yi-34b", "displayName": "nous-hermes-2-yi-34b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/nous-hermes-2-yi-34b" ], "manual_model_modalities_note": "Fireworks page identifies this as a base LLM and says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-nous-hermes-llama2-13b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "nous-hermes-llama2-13b", "displayName": "nous-hermes-llama2-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/nous-hermes-llama2-13b" ], "manual_model_modalities_note": "Fireworks page identifies this as a base LLM and says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-nous-hermes-llama2-70b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "nous-hermes-llama2-70b", "displayName": "nous-hermes-llama2-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/nous-hermes-llama2-70b" ], "manual_model_modalities_note": "Fireworks page identifies this as a base LLM and says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-nous-hermes-llama2-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "nous-hermes-llama2-7b", "displayName": "nous-hermes-llama2-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/nous-hermes-llama2-7b" ], "manual_model_modalities_note": "Fireworks page identifies this as a base LLM and says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-nvidia-nemotron-nano-12b-v2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "nvidia-nemotron-nano-12b-v2", "displayName": "nvidia-nemotron-nano-12b-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/nvidia-nemotron-nano-12b-v2" ], "manual_model_modalities_note": "Fireworks page identifies this as a base LLM and says image input is not supported." }, "benchmarks": { "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-nvidia-nemotron-nano-9b-v2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "nvidia-nemotron-nano-9b-v2", "displayName": "nvidia-nemotron-nano-9b-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/nvidia-nemotron-nano-9b-v2", "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2" ], "manual_model_modalities_note": "Fireworks labels it as an LLM and the official Nvidia model card is text generation." }, "benchmarks": { "local_mtbench_total_nemotron4340binstruct_officialmodelcard_184": { "label": "MT-Bench", "category": "preference", "score": 8.22, "scoreText": "8.22", "metric": "total", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_promptstrictacc_nemotron4340binstruct_officialmodelcard_185": { "label": "IFEval", "category": "agentic", "score": 79.9, "scoreText": "79.9", "metric": "Prompt-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_ifeval_instructionstrictacc_nemotron4340binstruct_officialmodelcard_186": { "label": "IFEval", "category": "agentic", "score": 86.1, "scoreText": "86.1", "metric": "Instruction-Strict Acc", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mmlu_0shot_nemotron4340binstruct_officialmodelcard_187": { "label": "MMLU", "category": "general_knowledge", "score": 78.7, "scoreText": "78.7", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_gsm8k_0shot_nemotron4340binstruct_officialmodelcard_188": { "label": "GSM8K", "category": "math", "score": 92.3, "scoreText": "92.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_humaneval_0shot_nemotron4340binstruct_officialmodelcard_189": { "label": "HumanEval", "category": "coding", "score": 73.2, "scoreText": "73.2", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_mbpp_0shot_nemotron4340binstruct_officialmodelcard_190": { "label": "MBPP", "category": "coding", "score": 75.4, "scoreText": "75.4", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_arenahard_arenahard_nemotron4340binstruct_officialmodelcard_191": { "label": "Arena Hard", "category": "preference", "score": 54.2, "scoreText": "54.2", "metric": "Arena Hard", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_alpacaeval20lc_lengthcontrolled_nemotron4340binstruct_officialmodelcard_192": { "label": "AlpacaEval 2.0 LC", "category": "preference", "score": 41.5, "scoreText": "41.5", "metric": "Length Controlled", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "Nemotron-4-340B-Instruct", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Nemotron-4-340B-Instruct evaluation table." }, "local_aime25_reasoningon_nvidianemotronnano12bv2_officialmodelcard_193": { "label": "AIME 2025", "category": "math", "score": 76.25, "scoreText": "76.25%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_math500_reasoningon_nvidianemotronnano12bv2_officialmodelcard_194": { "label": "MATH-500", "category": "math", "score": 97.75, "scoreText": "97.75%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_gpqa_reasoningon_nvidianemotronnano12bv2_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 64.48, "scoreText": "64.48%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_lcb_reasoningon_nvidianemotronnano12bv2_officialmodelcard_196": { "label": "LCB", "category": "other", "score": 70.79, "scoreText": "70.79%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_bfclv3_reasoningon_nvidianemotronnano12bv2_officialmodelcard_197": { "label": "BFCL", "category": "agentic", "score": 66.98, "scoreText": "66.98%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalprompt_reasoningon_nvidianemotronnano12bv2_officialmodelcard_198": { "label": "IFEval Prompt", "category": "agentic", "score": 84.7, "scoreText": "84.70%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." }, "local_ifevalinstruction_reasoningon_nvidianemotronnano12bv2_officialmodelcard_199": { "label": "IFEval Instruction", "category": "agentic", "score": 89.81, "scoreText": "89.81%", "metric": "Reasoning On", "higherIsBetter": true, "source_url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2", "checked_at": "2026-05-31", "baseModelFamily": "Nemotron", "exactModelOrSnapshot": "NVIDIA-Nemotron-Nano-12B-v2", "modelDeveloper": "NVIDIA", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official NVIDIA-Nemotron-Nano-12B-v2 benchmark table in Reasoning On mode." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-openchat-3p5-0106-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "openchat-3p5-0106-7b", "displayName": "openchat-3p5-0106-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/openchat-3p5-0106-7b" ], "manual_model_modalities_note": "Official model page shows image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-openhermes-2-mistral-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "openhermes-2-mistral-7b", "displayName": "openhermes-2-mistral-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/openhermes-2-mistral-7b", "https://huggingface.co/teknium/OpenHermes-2-Mistral-7B" ], "manual_model_modalities_note": "Fireworks model page plus the upstream model card identify it as text generation." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-openhermes-2p5-mistral-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "openhermes-2p5-mistral-7b", "displayName": "openhermes-2p5-mistral-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/openhermes-2p5-mistral-7b", "https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B" ], "manual_model_modalities_note": "Fireworks model page plus the upstream model card identify it as text generation." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/openorca-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-openorca-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "openorca-7b", "displayName": "openorca-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/openorca-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/openorca-7b", "https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca" ], "manual_model_modalities_note": "Fireworks model page plus the upstream model card identify it as text generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/phi-2-3b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-phi-2-3b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "phi-2-3b", "displayName": "phi-2-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/phi-2-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/phi-2-3b", "https://huggingface.co/microsoft/phi-2" ], "manual_model_modalities_note": "Fireworks marks image input as not supported and the upstream model card is text generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-phi-3-mini-128k-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "phi-3-mini-128k-instruct", "displayName": "phi-3-mini-128k-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/phi-3-mini-128k-instruct" ], "manual_model_modalities_note": "Official model page shows image input is not supported." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-phi-3-vision-128k-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "phi-3-vision-128k-instruct", "displayName": "phi-3-vision-128k-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32064, "maxInputTokens": 32064, "maxOutputTokens": 32064, "maxTokens": 32064, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32064, "max_input_tokens": 32064, "max_output_tokens": 32064, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/phi-3-vision-128k-instruct" ], "manual_model_modalities_note": "Official model page describes the model as multimodal and shows image input supported; output normalized to text." }, "benchmarks": { "mmlu_5shot_phi3small128kinstruct_officialmodelcard_198": { "label": "MMLU", "category": "general_knowledge", "score": 75.5, "scoreText": "75.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "arcchallenge_10shot_phi3small128kinstruct_officialmodelcard_199": { "label": "ARC-Challenge", "category": "reasoning", "score": 90.8, "scoreText": "90.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_200": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "humaneval_0shot_phi3small128kinstruct_officialmodelcard_201": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card; used the 128K benchmark table." }, "local_agieval_5shot_phi3mini128kinstruct_officialmodelcard_165": { "label": "AGI Eval", "category": "general_knowledge", "score": 39.5, "scoreText": "39.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_mmlu_5shot_phi3mini128kinstruct_officialmodelcard_166": { "label": "MMLU", "category": "general_knowledge", "score": 69.7, "scoreText": "69.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_bigbenchhard_3shot_phi3mini128kinstruct_officialmodelcard_167": { "label": "BigBench Hard", "category": "reasoning", "score": 72.1, "scoreText": "72.1", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_anli_7shot_phi3mini128kinstruct_officialmodelcard_168": { "label": "ANLI", "category": "reasoning", "score": 52.3, "scoreText": "52.3", "metric": "7-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_hellaswag_5shot_phi3mini128kinstruct_officialmodelcard_169": { "label": "HellaSwag", "category": "reasoning", "score": 70.5, "scoreText": "70.5", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arcchallenge_10shot_phi3mini128kinstruct_officialmodelcard_170": { "label": "ARC-Challenge", "category": "reasoning", "score": 85.5, "scoreText": "85.5", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Mini-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Mini 128K model card comparison table." }, "local_arceasy_10shot_phi3small128kinstruct_officialmodelcard_171": { "label": "ARC Easy", "category": "reasoning", "score": 97.3, "scoreText": "97.3", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_boolq_2shot_phi3small128kinstruct_officialmodelcard_172": { "label": "BoolQ", "category": "reasoning", "score": 83.7, "scoreText": "83.7", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_commonsenseqa_10shot_phi3small128kinstruct_officialmodelcard_173": { "label": "CommonsenseQA", "category": "general_knowledge", "score": 80.8, "scoreText": "80.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_medqa_2shot_phi3small128kinstruct_officialmodelcard_174": { "label": "MedQA", "category": "science", "score": 46.3, "scoreText": "46.3", "metric": "2-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_openbookqa_10shot_phi3small128kinstruct_officialmodelcard_175": { "label": "OpenBookQA", "category": "science", "score": 87.8, "scoreText": "87.8", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_piqa_5shot_phi3small128kinstruct_officialmodelcard_176": { "label": "PIQA", "category": "reasoning", "score": 88.1, "scoreText": "88.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_socialiqa_5shot_phi3small128kinstruct_officialmodelcard_177": { "label": "Social IQA", "category": "reasoning", "score": 78.7, "scoreText": "78.7", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_truthfulqamc2_10shot_phi3small128kinstruct_officialmodelcard_178": { "label": "TruthfulQA (MC2)", "category": "general_knowledge", "score": 69.6, "scoreText": "69.6", "metric": "10-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_winogrande_5shot_phi3small128kinstruct_officialmodelcard_179": { "label": "WinoGrande", "category": "reasoning", "score": 80.1, "scoreText": "80.1", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_triviaqa_5shot_phi3small128kinstruct_officialmodelcard_180": { "label": "TriviaQA", "category": "general_knowledge", "score": 66, "scoreText": "66.0", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_gsm8kchainofthought_8shot_phi3small128kinstruct_officialmodelcard_181": { "label": "GSM8K (CoT)", "category": "math", "score": 87.3, "scoreText": "87.3", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_humaneval_0shot_phi3small128kinstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 59.1, "scoreText": "59.1", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." }, "local_mbpp_3shot_phi3small128kinstruct_officialmodelcard_183": { "label": "MBPP", "category": "coding", "score": 70.3, "scoreText": "70.3", "metric": "3-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/microsoft/Phi-3-small-128k-instruct", "checked_at": "2026-05-31", "baseModelFamily": "Phi-3", "exactModelOrSnapshot": "Phi-3-Small-128K-Instruct", "modelDeveloper": "Microsoft", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Phi-3 Small 128K model card comparison table." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-phind-code-llama-34b-python-v1", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "phind-code-llama-34b-python-v1", "displayName": "phind-code-llama-34b-python-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/phind-code-llama-34b-python-v1" ], "manual_model_modalities_note": "Official model page shows image input is not supported." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-phind-code-llama-34b-v1", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "phind-code-llama-34b-v1", "displayName": "phind-code-llama-34b-v1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/phind-code-llama-34b-v1" ], "manual_model_modalities_note": "Official model page shows image input is not supported." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-phind-code-llama-34b-v2", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "phind-code-llama-34b-v2", "displayName": "phind-code-llama-34b-v2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/phind-code-llama-34b-v2" ], "manual_model_modalities_note": "Official model page shows image input is not supported." }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-playground-v2-1024px-aesthetic", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "playground-v2-1024px-aesthetic", "displayName": "playground-v2-1024px-aesthetic", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.00013, "outputUsdPer1MTokens": 0.00013, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.00013, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-playground-v2-5-1024px-aesthetic", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "playground-v2-5-1024px-aesthetic", "displayName": "playground-v2-5-1024px-aesthetic", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.00013, "outputUsdPer1MTokens": 0.00013, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.00013, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/pythia-12b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-pythia-12b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "pythia-12b", "displayName": "pythia-12b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 2048, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/pythia-12b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/pythia-12b" ], "manual_model_modalities_note": "Text-only; Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen-qwq-32b-preview", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen-qwq-32b-preview", "displayName": "qwen-qwq-32b-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen-qwq-32b-preview" ], "manual_model_modalities_note": "Text-only; Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen-v2p5-14b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen-v2p5-14b-instruct", "displayName": "qwen-v2p5-14b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen-v2p5-14b-instruct" ], "manual_model_modalities_note": "Text-only; Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen-v2p5-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen-v2p5-7b", "displayName": "qwen-v2p5-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen-v2p5-7b" ], "manual_model_modalities_note": "Text-only; Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen1p5-72b-chat", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen1p5-72b-chat", "displayName": "qwen1p5-72b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen1p5-72b-chat" ], "manual_model_modalities_note": "Text-only; Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2-7b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2-7b-instruct", "displayName": "qwen2-7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2-7b-instruct" ], "manual_model_modalities_note": "Text-only; Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2-vl-2b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2-vl-2b-instruct", "displayName": "qwen2-vl-2b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2-vl-2b-instruct" ], "manual_model_modalities_note": "Fireworks model page lists image input as supported." }, "benchmarks": { "local_mmmuval_score_qwen2vl7b_officialmodelcard_364": { "label": "MMMU", "category": "multimodal", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table compares Qwen2-VL-7B against InternVL2-8B, MiniCPM-V 2.6, and GPT-4o-mini." }, "local_docvqatest_score_qwen2vl7b_officialmodelcard_365": { "label": "DocVQA", "category": "multimodal", "score": 94.5, "scoreText": "94.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_infovqatest_score_qwen2vl7b_officialmodelcard_366": { "label": "InfoVQA", "category": "multimodal", "score": 76.5, "scoreText": "76.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_chartqatest_score_qwen2vl7b_officialmodelcard_367": { "label": "ChartQA", "category": "multimodal", "score": 83, "scoreText": "83.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_textvqaval_score_qwen2vl7b_officialmodelcard_368": { "label": "TextVQA", "category": "multimodal", "score": 84.3, "scoreText": "84.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_ocrbench_score_qwen2vl7b_officialmodelcard_369": { "label": "OCRBench", "category": "multimodal", "score": 845, "scoreText": "845", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_realworldqa_score_qwen2vl7b_officialmodelcard_370": { "label": "RealWorldQA", "category": "multimodal", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmbenchentest_score_qwen2vl7b_officialmodelcard_371": { "label": "MMBench-EN", "category": "multimodal", "score": 83, "scoreText": "83.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmbenchcntest_score_qwen2vl7b_officialmodelcard_372": { "label": "MMBench-CN", "category": "multimodal", "score": 80.5, "scoreText": "80.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmtbenchtest_score_qwen2vl7b_officialmodelcard_373": { "label": "MMT-Bench", "category": "multimodal", "score": 63.7, "scoreText": "63.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2-vl-72b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2-vl-72b-instruct", "displayName": "qwen2-vl-72b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2-vl-72b-instruct" ], "manual_model_modalities_note": "Fireworks model page lists image input as supported." }, "benchmarks": { "local_mmmuval_score_qwen2vl7b_officialmodelcard_364": { "label": "MMMU", "category": "multimodal", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table compares Qwen2-VL-7B against InternVL2-8B, MiniCPM-V 2.6, and GPT-4o-mini." }, "local_docvqatest_score_qwen2vl7b_officialmodelcard_365": { "label": "DocVQA", "category": "multimodal", "score": 94.5, "scoreText": "94.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_infovqatest_score_qwen2vl7b_officialmodelcard_366": { "label": "InfoVQA", "category": "multimodal", "score": 76.5, "scoreText": "76.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_chartqatest_score_qwen2vl7b_officialmodelcard_367": { "label": "ChartQA", "category": "multimodal", "score": 83, "scoreText": "83.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_textvqaval_score_qwen2vl7b_officialmodelcard_368": { "label": "TextVQA", "category": "multimodal", "score": 84.3, "scoreText": "84.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_ocrbench_score_qwen2vl7b_officialmodelcard_369": { "label": "OCRBench", "category": "multimodal", "score": 845, "scoreText": "845", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_realworldqa_score_qwen2vl7b_officialmodelcard_370": { "label": "RealWorldQA", "category": "multimodal", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmbenchentest_score_qwen2vl7b_officialmodelcard_371": { "label": "MMBench-EN", "category": "multimodal", "score": 83, "scoreText": "83.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmbenchcntest_score_qwen2vl7b_officialmodelcard_372": { "label": "MMBench-CN", "category": "multimodal", "score": 80.5, "scoreText": "80.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmtbenchtest_score_qwen2vl7b_officialmodelcard_373": { "label": "MMT-Bench", "category": "multimodal", "score": 63.7, "scoreText": "63.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2-vl-7b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2-vl-7b-instruct", "displayName": "qwen2-vl-7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2-vl-7b-instruct" ], "manual_model_modalities_note": "Fireworks model page lists image input as supported." }, "benchmarks": { "local_mmmuval_score_qwen2vl7b_officialmodelcard_364": { "label": "MMMU", "category": "multimodal", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table compares Qwen2-VL-7B against InternVL2-8B, MiniCPM-V 2.6, and GPT-4o-mini." }, "local_docvqatest_score_qwen2vl7b_officialmodelcard_365": { "label": "DocVQA", "category": "multimodal", "score": 94.5, "scoreText": "94.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_infovqatest_score_qwen2vl7b_officialmodelcard_366": { "label": "InfoVQA", "category": "multimodal", "score": 76.5, "scoreText": "76.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_chartqatest_score_qwen2vl7b_officialmodelcard_367": { "label": "ChartQA", "category": "multimodal", "score": 83, "scoreText": "83.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_textvqaval_score_qwen2vl7b_officialmodelcard_368": { "label": "TextVQA", "category": "multimodal", "score": 84.3, "scoreText": "84.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_ocrbench_score_qwen2vl7b_officialmodelcard_369": { "label": "OCRBench", "category": "multimodal", "score": 845, "scoreText": "845", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_realworldqa_score_qwen2vl7b_officialmodelcard_370": { "label": "RealWorldQA", "category": "multimodal", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmbenchentest_score_qwen2vl7b_officialmodelcard_371": { "label": "MMBench-EN", "category": "multimodal", "score": 83, "scoreText": "83.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmbenchcntest_score_qwen2vl7b_officialmodelcard_372": { "label": "MMBench-CN", "category": "multimodal", "score": 80.5, "scoreText": "80.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." }, "local_mmtbenchtest_score_qwen2vl7b_officialmodelcard_373": { "label": "MMT-Bench", "category": "multimodal", "score": 63.7, "scoreText": "63.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2-VL", "exactModelOrSnapshot": "Qwen2-VL-7B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model-card table; same snapshot column as above." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-0p5b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-0p5b-instruct", "displayName": "qwen2p5-0p5b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-0p5b-instruct" ], "manual_model_modalities_note": "Fireworks model page lists image input as not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-14b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-14b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-14b", "displayName": "qwen2p5-14b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-14b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-14b" ], "manual_model_modalities_note": "Fireworks model page lists image input as not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-1p5b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-1p5b-instruct", "displayName": "qwen2p5-1p5b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-1p5b-instruct" ], "manual_model_modalities_note": "Fireworks model page lists image input as not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-32b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-32b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-32b", "displayName": "qwen2p5-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-32b" ], "manual_model_modalities_note": "Fireworks model page describes this as a decoder-only language model and lists image input as not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-32b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-32b-instruct", "displayName": "qwen2p5-32b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-32b-instruct" ], "manual_model_modalities_note": "Fireworks model page describes this as a decoder-only language model and lists image input as not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-72b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-72b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-72b", "displayName": "qwen2p5-72b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-72b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-72b" ], "manual_model_modalities_note": "Fireworks model page describes this as a decoder-only language model and lists image input as not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-72b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-72b-instruct", "displayName": "qwen2p5-72b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-72b-instruct" ], "manual_model_modalities_note": "Fireworks model page describes this as a decoder-only language model and lists image input as not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-7b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-7b-instruct", "displayName": "qwen2p5-7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-7b-instruct" ], "manual_model_modalities_note": "Fireworks official model page lists image input as not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-0p5b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-0p5b", "displayName": "qwen2p5-coder-0p5b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-0p5b" ], "manual_model_modalities_note": "Fireworks official model page lists image input as not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-0p5b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-0p5b-instruct", "displayName": "qwen2p5-coder-0p5b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-0p5b-instruct", "https://fireworks.ai/docs/guides/querying-text-models" ], "manual_model_modalities_note": "Official Fireworks model page shows image input not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-14b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-14b", "displayName": "qwen2p5-coder-14b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-14b", "https://fireworks.ai/docs/guides/querying-text-models" ], "manual_model_modalities_note": "Official Fireworks model page shows image input not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-14b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-14b-instruct", "displayName": "qwen2p5-coder-14b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-14b-instruct", "https://fireworks.ai/docs/guides/querying-text-models" ], "manual_model_modalities_note": "Official Fireworks model page shows image input not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-1p5b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-1p5b", "displayName": "qwen2p5-coder-1p5b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-1p5b", "https://fireworks.ai/docs/guides/querying-text-models" ], "manual_model_modalities_note": "Official Fireworks model page shows image input not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-1p5b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-1p5b-instruct", "displayName": "qwen2p5-coder-1p5b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-1p5b-instruct", "https://fireworks.ai/docs/guides/querying-text-models" ], "manual_model_modalities_note": "Official Fireworks model page shows image input not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-32b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-32b", "displayName": "qwen2p5-coder-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-32b/", "https://fireworks.ai/docs/guides/querying-text-models" ], "manual_model_modalities_note": "Official Fireworks model page shows image input not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-32b-instruct-128k", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-32b-instruct-128k", "displayName": "qwen2p5-coder-32b-instruct-128k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-32b-instruct-128k", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Model page shows image input not supported; Fireworks text-model docs classify these as text models." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-32b-instruct-32k-rope", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-32b-instruct-32k-rope", "displayName": "qwen2p5-coder-32b-instruct-32k-rope", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-32b-instruct-32k-rope", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Model page shows image input not supported; Fireworks text-model docs classify these as text models." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-32b-instruct-64k", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-32b-instruct-64k", "displayName": "qwen2p5-coder-32b-instruct-64k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-32b-instruct-64k", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Model page shows image input not supported; Fireworks text-model docs classify these as text models." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-3b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-3b", "displayName": "qwen2p5-coder-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-3b", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Model page shows image input not supported; Fireworks text-model docs classify these as text models." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-3b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-3b-instruct", "displayName": "qwen2p5-coder-3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-3b-instruct", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Fireworks model-library page for the exact alias is a text model page and the docs classify these as text models." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-7b", "displayName": "qwen2p5-coder-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen2p5-coder-7b", "https://docs.fireworks.ai/guides/querying-text-models" ], "manual_model_modalities_note": "Model page shows image input not supported; Fireworks text-model docs classify these as text models." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-coder-7b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-coder-7b-instruct", "displayName": "qwen2p5-coder-7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct", "https://qwenlm.github.io/blog/qwen2.5-coder/" ], "manual_model_modalities_note": "Text-only." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-math-72b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-math-72b-instruct", "displayName": "qwen2p5-math-72b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen2.5-Math-72B-Instruct", "https://qwenlm.github.io/blog/qwen2.5-math/" ], "manual_model_modalities_note": "Text-only." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-vl-32b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-vl-32b-instruct", "displayName": "qwen2p5-vl-32b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.fireworks.ai/getting-started/quickstart", "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct" ], "manual_model_modalities_note": "Vision-language." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-vl-3b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-vl-3b-instruct", "displayName": "qwen2p5-vl-3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.fireworks.ai/updates/changelog", "https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct" ], "manual_model_modalities_note": "Vision-language." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-vl-72b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-vl-72b-instruct", "displayName": "qwen2p5-vl-72b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.fireworks.ai/updates/changelog", "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct" ], "manual_model_modalities_note": "Vision-language." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen2p5-vl-7b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen2p5-vl-7b-instruct", "displayName": "qwen2p5-vl-7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://docs.fireworks.ai/updates/changelog", "https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct" ], "manual_model_modalities_note": "Vision-language." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-0p6b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-0p6b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-0p6b", "displayName": "qwen3-0p6b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-0p6b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-0p6b" ], "manual_model_modalities_note": "Fireworks model page lists image input not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-14b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-14b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-14b", "displayName": "qwen3-14b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-14b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-14b" ], "manual_model_modalities_note": "Fireworks model page lists image input not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-1p7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-1p7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-1p7b", "displayName": "qwen3-1p7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-1p7b" ], "manual_model_modalities_note": "Fireworks model page lists image input not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-1p7b-fp8-draft", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-1p7b-fp8-draft", "displayName": "qwen3-1p7b-fp8-draft", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-1p7b-fp8-draft" ], "manual_model_modalities_note": "Fireworks model page lists image input not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-1p7b-fp8-draft-131072", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-1p7b-fp8-draft-131072", "displayName": "qwen3-1p7b-fp8-draft-131072", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-1p7b-fp8-draft", "https://huggingface.co/Qwen/Qwen3-1.7B" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported; upstream Qwen3-1.7B model card is text-generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-1p7b-fp8-draft-40960", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-1p7b-fp8-draft-40960", "displayName": "qwen3-1p7b-fp8-draft-40960", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-1p7b-fp8-draft", "https://huggingface.co/Qwen/Qwen3-1.7B" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported; upstream Qwen3-1.7B model card is text-generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-235b-a22b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-235b-a22b", "displayName": "qwen3-235b-a22b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-235b-a22b" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-235b-a22b-instruct-2507", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-235b-a22b-instruct-2507", "displayName": "qwen3-235b-a22b-instruct-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-235b-a22b-instruct-2507" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-235b-a22b-thinking-2507", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-235b-a22b-thinking-2507", "displayName": "qwen3-235b-a22b-thinking-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-235b-a22b-thinking-2507" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-30b-a3b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-30b-a3b", "displayName": "qwen3-30b-a3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-30b-a3b" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-30b-a3b-instruct-2507", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-30b-a3b-instruct-2507", "displayName": "qwen3-30b-a3b-instruct-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-7, "output_cost_per_token": 5e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-30b-a3b-instruct-2507", "https://fireworks.ai/models?modelTypes=Reranker%2CServerless%2CEmbedding%2CVision%2CLLM%2CImage&providers=Qwen" ], "manual_model_modalities_note": "Fireworks labels it as an LLM in the model library and the model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-30b-a3b-thinking-2507", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-30b-a3b-thinking-2507", "displayName": "qwen3-30b-a3b-thinking-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-30b-a3b-thinking-2507", "https://fireworks.ai/models?modelTypes=Reranker%2CServerless%2CEmbedding%2CVision%2CLLM%2CImage&providers=Qwen" ], "manual_model_modalities_note": "Fireworks labels it as an LLM in the model library and the model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-32b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-32b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-32b", "displayName": "qwen3-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-32b", "https://fireworks.ai/models?modelTypes=Reranker%2CServerless%2CEmbedding%2CVision%2CLLM%2CImage&providers=Qwen" ], "manual_model_modalities_note": "Fireworks describes it as a base language model and says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-4b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-4b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-4b", "displayName": "qwen3-4b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-4b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-4b", "https://fireworks.ai/models?modelTypes=Reranker%2CServerless%2CEmbedding%2CVision%2CLLM%2CImage&providers=Qwen" ], "manual_model_modalities_note": "Fireworks labels it as an LLM and the model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-4b-instruct-2507", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-4b-instruct-2507", "displayName": "qwen3-4b-instruct-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-4b-instruct-2507", "https://fireworks.ai/models?modelTypes=Reranker%2CServerless%2CEmbedding%2CVision%2CLLM%2CImage&providers=Qwen" ], "manual_model_modalities_note": "Fireworks labels it as an LLM and the model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-8b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-8b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-8b", "displayName": "qwen3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.fireworks.ai/updates/changelog" ], "checkedAt": "2026-06-02", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Fireworks changelog says serverless Qwen3 8B was removed on May 14, 2026; this exactly matches the Fireworks model slug." }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-8b", "https://fireworks.ai/models?modelTypes=Reranker%2CServerless%2CEmbedding%2CVision%2CLLM%2CImage&providers=Qwen" ], "manual_model_modalities_note": "Fireworks labels it as an LLM and the model page says image input is not supported.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.fireworks.ai/updates/changelog" ], "manual_model_lifecycle_checked_at": "2026-06-02", "manual_model_lifecycle_note": "Fireworks changelog says serverless Qwen3 8B was removed on May 14, 2026; this exactly matches the Fireworks model slug." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-coder-30b-a3b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-coder-30b-a3b-instruct", "displayName": "qwen3-coder-30b-a3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct" ], "manual_model_modalities_note": "Official Qwen model card shows text generation." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-coder-480b-instruct-bf16", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-coder-480b-instruct-bf16", "displayName": "qwen3-coder-480b-instruct-bf16", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct" ], "manual_model_modalities_note": "Official Qwen model card shows text generation." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-embedding-0p6b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-embedding-0p6b", "displayName": "qwen3-embedding-0p6b", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "fireworks_ai", "mode": "embedding" }, "benchmarks": { "local_qwen3evaluationsuite_mtebr_qwen3embedding06b_officialmodelcard_352": { "label": "Qwen3 evaluation suite", "category": "other", "score": 61.82, "scoreText": "61.82", "metric": "MTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_cmtebr_qwen3embedding06b_officialmodelcard_353": { "label": "Qwen3 evaluation suite", "category": "other", "score": 71.02, "scoreText": "71.02", "metric": "CMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mmtebr_qwen3embedding06b_officialmodelcard_354": { "label": "Qwen3 evaluation suite", "category": "other", "score": 64.64, "scoreText": "64.64", "metric": "MMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mldr_qwen3embedding06b_officialmodelcard_355": { "label": "Qwen3 evaluation suite", "category": "other", "score": 50.26, "scoreText": "50.26", "metric": "MLDR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mtebcode_qwen3embedding06b_officialmodelcard_356": { "label": "Qwen3 evaluation suite", "category": "other", "score": 75.41, "scoreText": "75.41", "metric": "MTEB-Code", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_followir_qwen3embedding06b_officialmodelcard_357": { "label": "Qwen3 evaluation suite", "category": "other", "score": 5.09, "scoreText": "5.09", "metric": "FollowIR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-embedding-4b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-embedding-4b", "displayName": "qwen3-embedding-4b", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "fireworks_ai", "mode": "embedding" }, "benchmarks": { "local_qwen3evaluationsuite_mtebr_qwen3embedding06b_officialmodelcard_352": { "label": "Qwen3 evaluation suite", "category": "other", "score": 61.82, "scoreText": "61.82", "metric": "MTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_cmtebr_qwen3embedding06b_officialmodelcard_353": { "label": "Qwen3 evaluation suite", "category": "other", "score": 71.02, "scoreText": "71.02", "metric": "CMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mmtebr_qwen3embedding06b_officialmodelcard_354": { "label": "Qwen3 evaluation suite", "category": "other", "score": 64.64, "scoreText": "64.64", "metric": "MMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mldr_qwen3embedding06b_officialmodelcard_355": { "label": "Qwen3 evaluation suite", "category": "other", "score": 50.26, "scoreText": "50.26", "metric": "MLDR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mtebcode_qwen3embedding06b_officialmodelcard_356": { "label": "Qwen3 evaluation suite", "category": "other", "score": 75.41, "scoreText": "75.41", "metric": "MTEB-Code", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_followir_qwen3embedding06b_officialmodelcard_357": { "label": "Qwen3 evaluation suite", "category": "other", "score": 5.09, "scoreText": "5.09", "metric": "FollowIR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "models", "displayName": "models", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "litellm_provider": "fireworks_ai", "mode": "embedding" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-next-80b-a3b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-next-80b-a3b-instruct", "displayName": "qwen3-next-80b-a3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct" ], "manual_model_modalities_note": "Official Qwen model card shows text generation." }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-next-80b-a3b-thinking", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-next-80b-a3b-thinking", "displayName": "qwen3-next-80b-a3b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking" ], "manual_model_modalities_note": "Official Qwen model card shows text generation." }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-reranker-0p6b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-reranker-0p6b", "displayName": "qwen3-reranker-0p6b", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "fireworks_ai", "mode": "rerank", "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "local_qwen3evaluationsuite_mtebr_qwen3reranker06b_officialmodelcard_358": { "label": "Qwen3 evaluation suite", "category": "other", "score": 65.8, "scoreText": "65.80", "metric": "MTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_cmtebr_qwen3reranker06b_officialmodelcard_359": { "label": "Qwen3 evaluation suite", "category": "other", "score": 71.31, "scoreText": "71.31", "metric": "CMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mmtebr_qwen3reranker06b_officialmodelcard_360": { "label": "Qwen3 evaluation suite", "category": "other", "score": 66.36, "scoreText": "66.36", "metric": "MMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mldr_qwen3reranker06b_officialmodelcard_361": { "label": "Qwen3 evaluation suite", "category": "other", "score": 67.28, "scoreText": "67.28", "metric": "MLDR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mtebcode_qwen3reranker06b_officialmodelcard_362": { "label": "Qwen3 evaluation suite", "category": "other", "score": 73.42, "scoreText": "73.42", "metric": "MTEB-Code", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_followir_qwen3reranker06b_officialmodelcard_363": { "label": "Qwen3 evaluation suite", "category": "other", "score": 5.41, "scoreText": "5.41", "metric": "FollowIR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-reranker-4b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-reranker-4b", "displayName": "qwen3-reranker-4b", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "fireworks_ai", "mode": "rerank", "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "local_qwen3evaluationsuite_mtebr_qwen3reranker06b_officialmodelcard_358": { "label": "Qwen3 evaluation suite", "category": "other", "score": 65.8, "scoreText": "65.80", "metric": "MTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_cmtebr_qwen3reranker06b_officialmodelcard_359": { "label": "Qwen3 evaluation suite", "category": "other", "score": 71.31, "scoreText": "71.31", "metric": "CMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mmtebr_qwen3reranker06b_officialmodelcard_360": { "label": "Qwen3 evaluation suite", "category": "other", "score": 66.36, "scoreText": "66.36", "metric": "MMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mldr_qwen3reranker06b_officialmodelcard_361": { "label": "Qwen3 evaluation suite", "category": "other", "score": 67.28, "scoreText": "67.28", "metric": "MLDR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mtebcode_qwen3reranker06b_officialmodelcard_362": { "label": "Qwen3 evaluation suite", "category": "other", "score": 73.42, "scoreText": "73.42", "metric": "MTEB-Code", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_followir_qwen3reranker06b_officialmodelcard_363": { "label": "Qwen3 evaluation suite", "category": "other", "score": 5.41, "scoreText": "5.41", "metric": "FollowIR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-reranker-8b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-reranker-8b", "displayName": "qwen3-reranker-8b", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": 40960, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "fireworks_ai", "mode": "rerank", "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "local_qwen3evaluationsuite_mtebr_qwen3reranker06b_officialmodelcard_358": { "label": "Qwen3 evaluation suite", "category": "other", "score": 65.8, "scoreText": "65.80", "metric": "MTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_cmtebr_qwen3reranker06b_officialmodelcard_359": { "label": "Qwen3 evaluation suite", "category": "other", "score": 71.31, "scoreText": "71.31", "metric": "CMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mmtebr_qwen3reranker06b_officialmodelcard_360": { "label": "Qwen3 evaluation suite", "category": "other", "score": 66.36, "scoreText": "66.36", "metric": "MMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mldr_qwen3reranker06b_officialmodelcard_361": { "label": "Qwen3 evaluation suite", "category": "other", "score": 67.28, "scoreText": "67.28", "metric": "MLDR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mtebcode_qwen3reranker06b_officialmodelcard_362": { "label": "Qwen3 evaluation suite", "category": "other", "score": 73.42, "scoreText": "73.42", "metric": "MTEB-Code", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_followir_qwen3reranker06b_officialmodelcard_363": { "label": "Qwen3 evaluation suite", "category": "other", "score": 5.41, "scoreText": "5.41", "metric": "FollowIR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-vl-235b-a22b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-vl-235b-a22b-instruct", "displayName": "qwen3-vl-235b-a22b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct" ], "manual_model_modalities_note": "Official Qwen model card shows image-text-to-text." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-vl-235b-a22b-thinking", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-vl-235b-a22b-thinking", "displayName": "qwen3-vl-235b-a22b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.22, "outputUsdPer1MTokens": 0.88, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.22, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Thinking" ], "manual_model_modalities_note": "Official Qwen model card shows image-text-to-text." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-vl-30b-a3b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-vl-30b-a3b-instruct", "displayName": "qwen3-vl-30b-a3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.fireworks.ai/updates/changelog" ], "checkedAt": "2026-06-02", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Fireworks changelog says serverless Qwen3 VL 30B A3B Instruct was removed on May 14, 2026; this exactly matches the Fireworks model slug." }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-vl-30b-a3b-instruct" ], "manual_model_modalities_note": "Fireworks model page describes this as a vision-language model and marks image input as supported.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.fireworks.ai/updates/changelog" ], "manual_model_lifecycle_checked_at": "2026-06-02", "manual_model_lifecycle_note": "Fireworks changelog says serverless Qwen3 VL 30B A3B Instruct was removed on May 14, 2026; this exactly matches the Fireworks model slug." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-vl-30b-a3b-thinking", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-vl-30b-a3b-thinking", "displayName": "qwen3-vl-30b-a3b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null, "status": "retired", "announcementDate": null, "shutdownDate": "2026-05-14", "earliestShutdownDate": null, "sourceUrls": [ "https://docs.fireworks.ai/updates/changelog" ], "checkedAt": "2026-06-02", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Fireworks changelog says serverless Qwen3 VL 30B A3B Thinking was removed on May 14, 2026; this exactly matches the Fireworks model slug." }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-vl-30b-a3b-thinking" ], "manual_model_modalities_note": "Fireworks model page describes this as a vision-language model and marks image input as supported.", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://docs.fireworks.ai/updates/changelog" ], "manual_model_lifecycle_checked_at": "2026-06-02", "manual_model_lifecycle_note": "Fireworks changelog says serverless Qwen3 VL 30B A3B Thinking was removed on May 14, 2026; this exactly matches the Fireworks model slug." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-vl-32b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-vl-32b-instruct", "displayName": "qwen3-vl-32b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-vl-32b-instruct" ], "manual_model_modalities_note": "Fireworks model page describes this as a vision-language model and marks image input as supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwen3-vl-8b-instruct", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwen3-vl-8b-instruct", "displayName": "qwen3-vl-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwen3-vl-8b-instruct" ], "manual_model_modalities_note": "Fireworks model page describes this as a vision-language model and marks image input as supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/qwq-32b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-qwq-32b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "qwq-32b", "displayName": "qwq-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/qwq-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/qwq-32b", "https://huggingface.co/Qwen/QwQ-32B" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported; upstream QwQ-32B model card is text-generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/rolm-ocr", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-rolm-ocr", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "rolm-ocr", "displayName": "rolm-ocr", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 128000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "image", "pdf", "text" ], "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/rolm-ocr", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/rolm-ocr" ], "manual_model_modalities_note": "Fireworks model page says it extracts plain text from PDFs, images, and other document formats." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-snorkel-mistral-7b-pairrm-dpo", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "snorkel-mistral-7b-pairrm-dpo", "displayName": "snorkel-mistral-7b-pairrm-dpo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/snorkel-mistral-7b-pairrm-dpo", "https://huggingface.co/SnorkelAI/Snorkel-Mistral-PairRM-DPO" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported; upstream Snorkel model card is text-generation." }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-stable-diffusion-xl-1024-v1-0", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "stable-diffusion-xl-1024-v1-0", "displayName": "stable-diffusion-xl-1024-v1-0", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 0.00013, "outputUsdPer1MTokens": 0.00013, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.00013, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/stablecode-3b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-stablecode-3b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "stablecode-3b", "displayName": "stablecode-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/stablecode-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/stablecode-3b", "https://huggingface.co/stabilityai/stablecode-3b" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported; upstream Stability AI model card is text-generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/starcoder-16b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-starcoder-16b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "starcoder-16b", "displayName": "starcoder-16b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/starcoder-16b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/starcoder-16b", "https://huggingface.co/bigcode/starcoder" ], "manual_model_modalities_note": "Fireworks model page marks image input unsupported and identifies provider Hugging Face bigcode/starcoder; the official BigCode model card is text generation." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/starcoder-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-starcoder-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "starcoder-7b", "displayName": "starcoder-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/starcoder-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/starcoder-7b", "https://huggingface.co/bigcode/starcoderbase-7b" ], "manual_model_modalities_note": "Supported via Fireworks model page and upstream BigCode model card; text-only." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/starcoder2-15b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-starcoder2-15b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "starcoder2-15b", "displayName": "starcoder2-15b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/starcoder2-15b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/starcoder2-15b", "https://huggingface.co/bigcode/starcoder2-15b" ], "manual_model_modalities_note": "Supported via Fireworks model page and upstream BigCode model card; text-only." }, "benchmarks": { "local_cruxevali_pass1_bigcodestarcoder215b_officialmodelcard_238": { "label": "CruxEval-I", "category": "coding", "score": 48.1, "scoreText": "48.100", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_ds1000_pass1_bigcodestarcoder215b_officialmodelcard_239": { "label": "DS-1000", "category": "coding", "score": 33.8, "scoreText": "33.800", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_gsm8kpal_accuracy_bigcodestarcoder215b_officialmodelcard_240": { "label": "GSM8K (PAL)", "category": "math", "score": 65.1, "scoreText": "65.100", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_humaneval_pass1_bigcodestarcoder215b_officialmodelcard_241": { "label": "HumanEval", "category": "coding", "score": 37.8, "scoreText": "37.800", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_humaneval_pass1_bigcodestarcoder215b_officialmodelcard_242": { "label": "HumanEval", "category": "coding", "score": 46.3, "scoreText": "46.300", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_repobenchv11_editsimilarity_bigcodestarcoder215b_officialmodelcard_243": { "label": "RepoBench-v1.1", "category": "coding", "score": 74.08, "scoreText": "74.080", "metric": "edit-similarity", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/starcoder2-3b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-starcoder2-3b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "starcoder2-3b", "displayName": "starcoder2-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/starcoder2-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/starcoder2-3b", "https://huggingface.co/bigcode/starcoder2-3b" ], "manual_model_modalities_note": "Supported via Fireworks model page and upstream BigCode model card; text-only." }, "benchmarks": { "local_cruxevali_pass1_bigcodestarcoder215b_officialmodelcard_238": { "label": "CruxEval-I", "category": "coding", "score": 48.1, "scoreText": "48.100", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_ds1000_pass1_bigcodestarcoder215b_officialmodelcard_239": { "label": "DS-1000", "category": "coding", "score": 33.8, "scoreText": "33.800", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_gsm8kpal_accuracy_bigcodestarcoder215b_officialmodelcard_240": { "label": "GSM8K (PAL)", "category": "math", "score": 65.1, "scoreText": "65.100", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_humaneval_pass1_bigcodestarcoder215b_officialmodelcard_241": { "label": "HumanEval", "category": "coding", "score": 37.8, "scoreText": "37.800", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_humaneval_pass1_bigcodestarcoder215b_officialmodelcard_242": { "label": "HumanEval", "category": "coding", "score": 46.3, "scoreText": "46.300", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_repobenchv11_editsimilarity_bigcodestarcoder215b_officialmodelcard_243": { "label": "RepoBench-v1.1", "category": "coding", "score": 74.08, "scoreText": "74.080", "metric": "edit-similarity", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/starcoder2-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-starcoder2-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "starcoder2-7b", "displayName": "starcoder2-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/starcoder2-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/starcoder2-7b", "https://huggingface.co/bigcode/starcoder2-7b" ], "manual_model_modalities_note": "Supported via Fireworks model page and upstream BigCode model card; text-only." }, "benchmarks": { "local_cruxevali_pass1_bigcodestarcoder215b_officialmodelcard_238": { "label": "CruxEval-I", "category": "coding", "score": 48.1, "scoreText": "48.100", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_ds1000_pass1_bigcodestarcoder215b_officialmodelcard_239": { "label": "DS-1000", "category": "coding", "score": 33.8, "scoreText": "33.800", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_gsm8kpal_accuracy_bigcodestarcoder215b_officialmodelcard_240": { "label": "GSM8K (PAL)", "category": "math", "score": 65.1, "scoreText": "65.100", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_humaneval_pass1_bigcodestarcoder215b_officialmodelcard_241": { "label": "HumanEval", "category": "coding", "score": 37.8, "scoreText": "37.800", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_humaneval_pass1_bigcodestarcoder215b_officialmodelcard_242": { "label": "HumanEval", "category": "coding", "score": 46.3, "scoreText": "46.300", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." }, "local_repobenchv11_editsimilarity_bigcodestarcoder215b_officialmodelcard_243": { "label": "RepoBench-v1.1", "category": "coding", "score": 74.08, "scoreText": "74.080", "metric": "edit-similarity", "higherIsBetter": true, "source_url": "https://huggingface.co/bigcode/starcoder2-15b", "checked_at": "2026-05-31", "baseModelFamily": "StarCoder2", "exactModelOrSnapshot": "bigcode/starcoder2-15b", "modelDeveloper": "BigCode", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported in the official model card." } } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/toppy-m-7b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-toppy-m-7b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "toppy-m-7b", "displayName": "toppy-m-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/toppy-m-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/toppy-m-7b", "https://huggingface.co/Undi95/Toppy-M-7B" ], "manual_model_modalities_note": "Supported via Fireworks model page and upstream Hugging Face model card; text-only." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/whisper-v3", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-whisper-v3", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "whisper-v3", "displayName": "whisper-v3", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/whisper-v3", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "fireworks_ai", "mode": "audio_transcription", "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/whisper-v3-turbo", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-whisper-v3-turbo", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "whisper-v3-turbo", "displayName": "whisper-v3-turbo", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/whisper-v3-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "fireworks_ai", "mode": "audio_transcription", "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/yi-34b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-yi-34b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "yi-34b", "displayName": "yi-34b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/yi-34b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/yi-01-ai/yi-34b", "https://huggingface.co/01-ai/Yi-34B" ], "manual_model_modalities_note": "Supported via Fireworks model page and upstream 01.AI model card; text-only." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-yi-34b-200k-capybara", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "yi-34b-200k-capybara", "displayName": "yi-34b-200k-capybara", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 200000, "maxInputTokens": 200000, "maxOutputTokens": 200000, "maxTokens": 200000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/yi-34b-200k-capybara" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/yi-34b-chat", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-yi-34b-chat", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "yi-34b-chat", "displayName": "yi-34b-chat", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.8999999999999999, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.8999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/yi-34b-chat", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/yi-01-ai/yi-34b-chat" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/yi-6b", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-yi-6b", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "yi-6b", "displayName": "yi-6b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 4096, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/yi-6b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/yi-01-ai/yi-6b" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." } }, { "id": "fireworks_ai/fireworks_ai/accounts/fireworks/models/zephyr-7b-beta", "slug": "fireworks_ai-fireworks_ai-accounts-fireworks-models-zephyr-7b-beta", "provider": "fireworks_ai", "providerSlug": "fireworks_ai", "name": "zephyr-7b-beta", "displayName": "zephyr-7b-beta", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "litellm_provider": "fireworks_ai", "mode": "chat", "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://fireworks.ai/models/fireworks/zephyr-7b-beta" ], "manual_model_modalities_note": "Official Fireworks model page says image input is not supported." } }, { "id": "novita/novita/deepseek/deepseek-v3.2", "slug": "novita-novita-deepseek-deepseek-v3-2", "provider": "novita", "providerSlug": "novita", "name": "deepseek-v3.2", "displayName": "deepseek-v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.26899999999999996, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.13449999999999998, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.26899999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.69e-7, "output_cost_per_token": 4e-7, "cache_read_input_token_cost": 1.345e-7, "input_cost_per_token_cache_hit": 1.345e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 163840, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-v3.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.69e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 163840, "max_output_tokens": 65536, "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.345e-7, "input_cost_per_token_cache_hit": 1.345e-7, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/deepseek-deepseek-v3.2" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "novita/novita/minimax/minimax-m2.1", "slug": "novita-novita-minimax-minimax-m2-1", "provider": "novita", "providerSlug": "novita", "name": "minimax-m2.1", "displayName": "minimax-m2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "cache_read_input_token_cost": 3e-8, "input_cost_per_token_cache_hit": 3e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 204800, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/minimax/minimax-m2.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 3e-8, "input_cost_per_token_cache_hit": 3e-8, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/minimax-minimax-m2.1" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchverified_score_minimaxm21_officialmodelcard_212": { "label": "SWE-bench Verified", "category": "coding", "score": 74, "scoreText": "74.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_multiswebench_score_minimaxm21_officialmodelcard_213": { "label": "Multi-SWE-bench", "category": "coding", "score": 49.4, "scoreText": "49.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm21_officialmodelcard_214": { "label": "SWE-bench Multilingual", "category": "coding", "score": 72.5, "scoreText": "72.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_terminalbench20_score_minimaxm21_officialmodelcard_215": { "label": "Terminal-Bench 2.0", "category": "coding", "score": 47.9, "scoreText": "47.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card benchmark table." }, "local_vibeaverage_score_minimaxm21_officialmodelcard_216": { "label": "VIBE (Average)", "category": "multimodal", "score": 88.6, "scoreText": "88.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeweb_score_minimaxm21_officialmodelcard_217": { "label": "VIBE-Web", "category": "multimodal", "score": 91.5, "scoreText": "91.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." }, "local_vibeandroid_score_minimaxm21_officialmodelcard_218": { "label": "VIBE-Android", "category": "multimodal", "score": 89.7, "scoreText": "89.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2.1", "exactModelOrSnapshot": "MiniMax-M2.1", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2.1 model card VIBE table." } } }, { "id": "novita/novita/zai-org/glm-4.7", "slug": "novita-novita-zai-org-glm-4-7", "provider": "novita", "providerSlug": "novita", "name": "glm-4.7", "displayName": "glm-4.7", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token_cache_hit": 1.1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 204800, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/zai-org/glm-4.7", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token_cache_hit": 1.1e-7, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/llm/zai-org-glm-4.7" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "novita/novita/xiaomimimo/mimo-v2-flash", "slug": "novita-novita-xiaomimimo-mimo-v2-flash", "provider": "novita", "providerSlug": "novita", "name": "mimo-v2-flash", "displayName": "mimo-v2-flash", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": 0.02, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "cache_read_input_token_cost": 2e-8, "input_cost_per_token_cache_hit": 2e-8 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 262144, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/xiaomimimo/mimo-v2-flash", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 262144, "max_output_tokens": 32000, "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 2e-8, "input_cost_per_token_cache_hit": 2e-8, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/xiaomimimo-mimo-v2-flash" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/zai-org/autoglm-phone-9b-multilingual", "slug": "novita-novita-zai-org-autoglm-phone-9b-multilingual", "provider": "novita", "providerSlug": "novita", "name": "autoglm-phone-9b-multilingual", "displayName": "autoglm-phone-9b-multilingual", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.035, "outputUsdPer1MTokens": 0.13799999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.035, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.38e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 65536, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/zai-org/autoglm-phone-9b-multilingual", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.38e-7, "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "supports_vision": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/zai-org-autoglm-phone-9b-multilingual" ], "manual_model_modalities_note": "Novita model detail lists text and image input with text output." }, "benchmarks": { "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "novita/novita/moonshotai/kimi-k2-thinking", "slug": "novita-novita-moonshotai-kimi-k2-thinking", "provider": "novita", "providerSlug": "novita", "name": "kimi-k2-thinking", "displayName": "kimi-k2-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/moonshotai/kimi-k2-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/moonshotai-kimi-k2-thinking" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/minimax/minimax-m2", "slug": "novita-novita-minimax-minimax-m2", "provider": "novita", "providerSlug": "novita", "name": "minimax-m2", "displayName": "minimax-m2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "cache_read_input_token_cost": 3e-8, "input_cost_per_token_cache_hit": 3e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 204800, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/minimax/minimax-m2", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "cache_read_input_token_cost": 3e-8, "input_cost_per_token_cache_hit": 3e-8, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/minimax-minimax-m2" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_swebenchverified_score_minimaxm2_officialmodelcard_206": { "label": "SWE-bench Verified", "category": "coding", "score": 69.4, "scoreText": "69.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_multiswebench_score_minimaxm2_officialmodelcard_207": { "label": "Multi-SWE-bench", "category": "coding", "score": 36.2, "scoreText": "36.2", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_swebenchmultilingual_score_minimaxm2_officialmodelcard_208": { "label": "SWE-bench Multilingual", "category": "coding", "score": 56.5, "scoreText": "56.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_terminalbench_score_minimaxm2_officialmodelcard_209": { "label": "Terminal-Bench", "category": "coding", "score": 46.3, "scoreText": "46.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_artifactsbench_score_minimaxm2_officialmodelcard_210": { "label": "ArtifactsBench", "category": "other", "score": 66.8, "scoreText": "66.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." }, "local_browsecomp_score_minimaxm2_officialmodelcard_211": { "label": "BrowseComp", "category": "other", "score": 44, "scoreText": "44", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "checked_at": "2026-05-31", "baseModelFamily": "MiniMax-M2", "exactModelOrSnapshot": "MiniMax-M2", "modelDeveloper": "MiniMax", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the MiniMax-M2 model card benchmark table." } } }, { "id": "novita/novita/paddlepaddle/paddleocr-vl", "slug": "novita-novita-paddlepaddle-paddleocr-vl", "provider": "novita", "providerSlug": "novita", "name": "paddleocr-vl", "displayName": "paddleocr-vl", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": 0.02, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 2e-8 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/paddlepaddle/paddleocr-vl", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-8, "output_cost_per_token": 2e-8, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "supports_vision": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/paddlepaddle-paddleocr-vl" ], "manual_model_modalities_note": "Novita model detail lists text and image input with text output." } }, { "id": "novita/novita/deepseek/deepseek-v3.2-exp", "slug": "novita-novita-deepseek-deepseek-v3-2-exp", "provider": "novita", "providerSlug": "novita", "name": "deepseek-v3.2-exp", "displayName": "deepseek-v3.2-exp", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 0.41, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 4.1e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 163840, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-v3.2-exp", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.7e-7, "output_cost_per_token": 4.1e-7, "max_input_tokens": 163840, "max_output_tokens": 65536, "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/deepseek-deepseek-v3.2-exp" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_225": { "label": "Aider Polyglot", "category": "coding", "score": 74.2, "scoreText": "74.2%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek V3.2-Exp", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row labeled as the reasoner variant." }, "local_mmlupro_em_deepseekv32exp_officialmodelcard_106": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 85, "scoreText": "85.0", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_gpqadiamond_pass1_deepseekv32exp_officialmodelcard_107": { "label": "GPQA Diamond", "category": "science", "score": 79.9, "scoreText": "79.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_livecodebench_pass1_deepseekv32exp_officialmodelcard_108": { "label": "LiveCodeBench", "category": "coding", "score": 74.1, "scoreText": "74.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aime2025_pass1_deepseekv32exp_officialmodelcard_109": { "label": "AIME 2025", "category": "math", "score": 89.3, "scoreText": "89.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_aiderpolyglot_accuracy_deepseekv32exp_officialmodelcard_110": { "label": "Aider Polyglot", "category": "coding", "score": 74.5, "scoreText": "74.5", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_sweverified_resolved_deepseekv32exp_officialmodelcard_111": { "label": "SWE-bench Verified", "category": "agentic", "score": 67.8, "scoreText": "67.8", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_terminalbench_score_deepseekv32exp_officialmodelcard_112": { "label": "Terminal-Bench", "category": "agentic", "score": 37.7, "scoreText": "37.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2-Exp", "exactModelOrSnapshot": "DeepSeek-V3.2-Exp", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2-Exp card compares against V3.1-Terminus." }, "local_diamond_score_deepseekaideepseekv32_benchmarkleaderboard_113": { "label": "Diamond", "category": "science", "score": 82.4, "scoreText": "82.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_terminalbench2_score_deepseekaideepseekv32_benchmarkleaderboard_114": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 39.6, "scoreText": "39.6 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_apexagents_score_deepseekaideepseekv32_benchmarkleaderboard_115": { "label": "Apex Agents", "category": "agentic", "score": 7, "scoreText": "7 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." }, "local_swebenchpro_score_deepseekaideepseekv32_benchmarkleaderboard_116": { "label": "SWE-bench Pro", "category": "agentic", "score": 15.56, "scoreText": "15.56", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results." }, "local_swebenchverified_resolved_deepseekaideepseekv32_benchmarkleaderboard_117": { "label": "SWE-bench Verified", "category": "agentic", "score": 70, "scoreText": "70 *", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.2", "exactModelOrSnapshot": "deepseek-ai/DeepSeek-V3.2", "modelDeveloper": "DeepSeek-AI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official V3.2 model card embeds leaderboard-backed evaluation results; asterisk preserved from source." } } }, { "id": "novita/novita/qwen/qwen3-vl-235b-a22b-thinking", "slug": "novita-novita-qwen-qwen3-vl-235b-a22b-thinking", "provider": "novita", "providerSlug": "novita", "name": "qwen3-vl-235b-a22b-thinking", "displayName": "qwen3-vl-235b-a22b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.98, "outputUsdPer1MTokens": 3.95, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.98, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9.8e-7, "output_cost_per_token": 0.00000395 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-vl-235b-a22b-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 9.8e-7, "output_cost_per_token": 0.00000395, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-vl-235b-a22b-thinking" ], "manual_model_modalities_note": "Novita model detail lists text, image, and video input with text output." } }, { "id": "novita/novita/zai-org/glm-4.6v", "slug": "novita-novita-zai-org-glm-4-6v", "provider": "novita", "providerSlug": "novita", "name": "glm-4.6v", "displayName": "glm-4.6v", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.8999999999999999, "cachedInputUsdPer1MTokens": 0.055, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7, "cache_read_input_token_cost": 5.5e-8, "input_cost_per_token_cache_hit": 5.5e-8 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/zai-org/glm-4.6v", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 5.5e-8, "input_cost_per_token_cache_hit": 5.5e-8, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/zai-org-glm-4.6v" ], "manual_model_modalities_note": "Novita model detail lists text, image, and video input with text output." }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_zaiglm46_benchmarkleaderboard_282": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_zaiglm46_benchmarkleaderboard_283": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_zaiglm46_benchmarkleaderboard_284": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_zaiglm46_benchmarkleaderboard_285": { "label": "GPQA Diamond", "category": "reasoning", "score": 78, "scoreText": "78.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_artificialanalysisintelligenceindex_score_zaiglm46_benchmarkleaderboard_310": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysiscodingindex_score_zaiglm46_benchmarkleaderboard_311": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysisagenticindex_score_zaiglm46_benchmarkleaderboard_312": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." } } }, { "id": "novita/novita/zai-org/glm-4.6", "slug": "novita-novita-zai-org-glm-4-6", "provider": "novita", "providerSlug": "novita", "name": "glm-4.6", "displayName": "glm-4.6", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.55, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.55, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token_cache_hit": 1.1e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 204800, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/zai-org/glm-4.6", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token_cache_hit": 1.1e-7, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/zai-org-glm-4.6" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_zaiglm46_benchmarkleaderboard_282": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_zaiglm46_benchmarkleaderboard_283": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_zaiglm46_benchmarkleaderboard_284": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_zaiglm46_benchmarkleaderboard_285": { "label": "GPQA Diamond", "category": "reasoning", "score": 78, "scoreText": "78.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GLM 4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_artificialanalysisintelligenceindex_score_zaiglm46_benchmarkleaderboard_310": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 32.5, "scoreText": "32.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysiscodingindex_score_zaiglm46_benchmarkleaderboard_311": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 29.5, "scoreText": "29.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." }, "local_artificialanalysisagenticindex_score_zaiglm46_benchmarkleaderboard_312": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 41.6, "scoreText": "41.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/z-ai/glm-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "glm-4.6", "exactModelOrSnapshot": "z-ai/glm-4.6", "modelDeveloper": "Z.ai", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; multi-provider routing is used on the platform." } } }, { "id": "novita/novita/kwaipilot/kat-coder-pro", "slug": "novita-novita-kwaipilot-kat-coder-pro", "provider": "novita", "providerSlug": "novita", "name": "kat-coder-pro", "displayName": "kat-coder-pro", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.2, "cachedInputUsdPer1MTokens": 0.06, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "cache_read_input_token_cost": 6e-8, "input_cost_per_token_cache_hit": 6e-8 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 256000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/kwaipilot/kat-coder-pro", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 6e-8, "input_cost_per_token_cache_hit": 6e-8, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/kwaipilot-kat-coder-pro" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/qwen/qwen3-next-80b-a3b-instruct", "slug": "novita-novita-qwen-qwen3-next-80b-a3b-instruct", "provider": "novita", "providerSlug": "novita", "name": "qwen3-next-80b-a3b-instruct", "displayName": "qwen3-next-80b-a3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-next-80b-a3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-next-80b-a3b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "novita/novita/qwen/qwen3-next-80b-a3b-thinking", "slug": "novita-novita-qwen-qwen3-next-80b-a3b-thinking", "provider": "novita", "providerSlug": "novita", "name": "qwen3-next-80b-a3b-thinking", "displayName": "qwen3-next-80b-a3b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-next-80b-a3b-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-next-80b-a3b-thinking" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_mmlupro_score_qwen3next80ba3binstruct_officialmodelcard_50": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.6, "scoreText": "80.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_mmluredux_score_qwen3next80ba3binstruct_officialmodelcard_51": { "label": "MMLU-Redux", "category": "general_knowledge", "score": 90.9, "scoreText": "90.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_gpqa_score_qwen3next80ba3binstruct_officialmodelcard_52": { "label": "GPQA", "category": "science", "score": 72.9, "scoreText": "72.9", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_supergpqa_score_qwen3next80ba3binstruct_officialmodelcard_53": { "label": "SuperGPQA", "category": "science", "score": 58.8, "scoreText": "58.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aime25_score_qwen3next80ba3binstruct_officialmodelcard_54": { "label": "AIME 2025", "category": "math", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_hmmt25_score_qwen3next80ba3binstruct_officialmodelcard_55": { "label": "HMMT25", "category": "math", "score": 54.1, "scoreText": "54.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livebench20241125_score_qwen3next80ba3binstruct_officialmodelcard_56": { "label": "LiveBench 20241125", "category": "general_knowledge", "score": 75.8, "scoreText": "75.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_livecodebenchv625022505_score_qwen3next80ba3binstruct_officialmodelcard_57": { "label": "LiveCodeBench v6", "category": "coding", "score": 56.6, "scoreText": "56.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_multiple_score_qwen3next80ba3binstruct_officialmodelcard_58": { "label": "MultiPL-E", "category": "coding", "score": 87.8, "scoreText": "87.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_aiderpolyglot_score_qwen3next80ba3binstruct_officialmodelcard_59": { "label": "Aider Polyglot", "category": "coding", "score": 49.8, "scoreText": "49.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card comparison table; only the Qwen3-Next column is recorded here." }, "local_ruler1m_accavg_qwen3next80ba3binstruct_officialmodelcard_60": { "label": "RULER 1M", "category": "long_context", "score": 91.8, "scoreText": "91.8", "metric": "Acc avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Next", "exactModelOrSnapshot": "Qwen3-Next-80B-A3B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Long-context evaluation from the model card; YaRN was enabled for the 1M test." } } }, { "id": "novita/novita/deepseek/deepseek-ocr", "slug": "novita-novita-deepseek-deepseek-ocr", "provider": "novita", "providerSlug": "novita", "name": "deepseek-ocr", "displayName": "deepseek-ocr", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.03, "outputUsdPer1MTokens": 0.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.03, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-8, "output_cost_per_token": 3e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-ocr", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-8, "output_cost_per_token": 3e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/deepseek-deepseek-ocr", "https://novita.ai/docs/guides/llm-deepseek-ocr" ], "manual_model_modalities_note": "Novita model detail and guide show text and image input with text output." } }, { "id": "novita/novita/deepseek/deepseek-v3.1-terminus", "slug": "novita-novita-deepseek-deepseek-v3-1-terminus", "provider": "novita", "providerSlug": "novita", "name": "deepseek-v3.1-terminus", "displayName": "deepseek-v3.1-terminus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": 0.135, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "cache_read_input_token_cost": 1.35e-7, "input_cost_per_token_cache_hit": 1.35e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-v3.1-terminus", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.35e-7, "input_cost_per_token_cache_hit": 1.35e-7, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/deepseek-deepseek-v3.1-terminus" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "novita/novita/qwen/qwen3-vl-235b-a22b-instruct", "slug": "novita-novita-qwen-qwen3-vl-235b-a22b-instruct", "provider": "novita", "providerSlug": "novita", "name": "qwen3-vl-235b-a22b-instruct", "displayName": "qwen3-vl-235b-a22b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-vl-235b-a22b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-vl-235b-a22b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text, image, and video input with text output." } }, { "id": "novita/novita/qwen/qwen3-max", "slug": "novita-novita-qwen-qwen3-max", "provider": "novita", "providerSlug": "novita", "name": "qwen3-max", "displayName": "qwen3-max", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 2.1100000000000003, "outputUsdPer1MTokens": 8.450000000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.1100000000000003, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000211, "output_cost_per_token": 0.00000845 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262144, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-max", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 0.00000211, "output_cost_per_token": 0.00000845, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-max" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "artificialanalysisintelligenceindex_indexscore_qwenqwen3max_benchmarkleaderboard_279": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 31.3, "scoreText": "31.3", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_qwenqwen3max_benchmarkleaderboard_280": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 26.4, "scoreText": "26.4", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_qwenqwen3max_benchmarkleaderboard_281": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 43, "scoreText": "43.0", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-max/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3 Max", "exactModelOrSnapshot": "qwen/qwen3-max", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "novita/novita/skywork/r1v4-lite", "slug": "novita-novita-skywork-r1v4-lite", "provider": "novita", "providerSlug": "novita", "name": "r1v4-lite", "displayName": "r1v4-lite", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262144, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/skywork/r1v4-lite", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true } }, { "id": "novita/novita/deepseek/deepseek-v3.1", "slug": "novita-novita-deepseek-deepseek-v3-1", "provider": "novita", "providerSlug": "novita", "name": "deepseek-v3.1", "displayName": "deepseek-v3.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": 0.135, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "cache_read_input_token_cost": 1.35e-7, "input_cost_per_token_cache_hit": 1.35e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-v3.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.35e-7, "input_cost_per_token_cache_hit": 1.35e-7, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/deepseek-deepseek-v3.1" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "local_mmlupro_em_deepseekv31thinking_officialmodelcard_99": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 84.8, "scoreText": "84.8", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekv31thinking_officialmodelcard_100": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_humanityslastexam_pass1_deepseekv31thinking_officialmodelcard_101": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 15.9, "scoreText": "15.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_livecodebench24082505_pass1_deepseekv31thinking_officialmodelcard_102": { "label": "LiveCodeBench", "category": "coding", "score": 74.8, "scoreText": "74.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekv31thinking_officialmodelcard_103": { "label": "Aider Polyglot", "category": "coding", "score": 76.3, "scoreText": "76.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_sweverifiedagentmode_resolved_deepseekv31thinking_officialmodelcard_104": { "label": "SWE-bench Verified (Agent mode)", "category": "agentic", "score": 66, "scoreText": "66.0", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." }, "local_aime2025_pass1_deepseekv31thinking_officialmodelcard_105": { "label": "AIME 2025", "category": "math", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3.1", "exactModelOrSnapshot": "DeepSeek-V3.1-Thinking", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "V3.1 evaluation table on the official model card." } } }, { "id": "novita/novita/moonshotai/kimi-k2-0905", "slug": "novita-novita-moonshotai-kimi-k2-0905", "provider": "novita", "providerSlug": "novita", "name": "kimi-k2-0905", "displayName": "kimi-k2-0905", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 262144, "maxInputTokens": 262144, "maxOutputTokens": 262144, "maxTokens": 262144, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/moonshotai/kimi-k2-0905", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/moonshotai-kimi-k2-0905" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/qwen/qwen3-coder-480b-a35b-instruct", "slug": "novita-novita-qwen-qwen3-coder-480b-a35b-instruct", "provider": "novita", "providerSlug": "novita", "name": "qwen3-coder-480b-a35b-instruct", "displayName": "qwen3-coder-480b-a35b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 1.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000013 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 262144, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-coder-480b-a35b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000013, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-coder-480b-a35b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "novita/novita/qwen/qwen3-coder-30b-a3b-instruct", "slug": "novita-novita-qwen-qwen3-coder-30b-a3b-instruct", "provider": "novita", "providerSlug": "novita", "name": "qwen3-coder-30b-a3b-instruct", "displayName": "qwen3-coder-30b-a3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.27, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.7e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 160000, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-coder-30b-a3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-8, "output_cost_per_token": 2.7e-7, "max_input_tokens": 160000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/qwen-qwen3-coder-30b-a3b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_terminalbench2_score_qwen3coder480ba35binstruct_officialmodelcard_61": { "label": "Terminal-Bench 2.0", "category": "agentic", "score": 23.9, "scoreText": "23.9 *", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; asterisk preserved from the source." }, "local_swebenchpro_score_qwen3coder480ba35binstruct_officialmodelcard_62": { "label": "SWE-bench Pro", "category": "agentic", "score": 38.7, "scoreText": "38.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section." }, "local_evasionbench_score_qwen3coder480ba35binstruct_officialmodelcard_63": { "label": "Evasion Bench", "category": "other", "score": 78.16, "scoreText": "78.16", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen3-Coder", "exactModelOrSnapshot": "Qwen3-Coder-480B-A35B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Captured from the model-card eval section; benchmark name preserved as published." }, "local_artificialanalysisintelligenceindex_score_qwenqwen3coder_benchmarkleaderboard_307": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.8, "scoreText": "24.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysiscodingindex_score_qwenqwen3coder_benchmarkleaderboard_308": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 24.6, "scoreText": "24.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." }, "local_artificialanalysisagenticindex_score_qwenqwen3coder_benchmarkleaderboard_309": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 18.3, "scoreText": "18.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen3-coder/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-coder", "exactModelOrSnapshot": "qwen/qwen3-coder", "modelDeveloper": "Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; route ordering is tuned for tool-calling accuracy." } } }, { "id": "novita/novita/openai/gpt-oss-120b", "slug": "novita-novita-openai-gpt-oss-120b", "provider": "novita", "providerSlug": "novita", "name": "gpt-oss-120b", "displayName": "gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/openai/gpt-oss-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/openai-gpt-oss-120b" ], "manual_model_modalities_note": "Novita model detail lists text and image input with text output." }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "novita/novita/moonshotai/kimi-k2-instruct", "slug": "novita-novita-moonshotai-kimi-k2-instruct", "provider": "novita", "providerSlug": "novita", "name": "kimi-k2-instruct", "displayName": "kimi-k2-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.5700000000000001, "outputUsdPer1MTokens": 2.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.5700000000000001, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.7e-7, "output_cost_per_token": 0.0000023 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/moonshotai/kimi-k2-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5.7e-7, "output_cost_per_token": 0.0000023, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/moonshotai-kimi-k2-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/deepseek/deepseek-v3-0324", "slug": "novita-novita-deepseek-deepseek-v3-0324", "provider": "novita", "providerSlug": "novita", "name": "deepseek-v3-0324", "displayName": "deepseek-v3-0324", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 1.12, "cachedInputUsdPer1MTokens": 0.135, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.00000112, "cache_read_input_token_cost": 1.35e-7, "input_cost_per_token_cache_hit": 1.35e-7 } }, "limits": { "contextWindow": 163840, "maxInputTokens": 163840, "maxOutputTokens": 163840, "maxTokens": 163840, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-v3-0324", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.00000112, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.35e-7, "input_cost_per_token_cache_hit": 1.35e-7, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/deepseek-deepseek-v3-0324" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "novita/novita/zai-org/glm-4.5", "slug": "novita-novita-zai-org-glm-4-5", "provider": "novita", "providerSlug": "novita", "name": "glm-4.5", "displayName": "glm-4.5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token_cache_hit": 1.1e-7 } }, "limits": { "contextWindow": 98304, "maxInputTokens": 131072, "maxOutputTokens": 98304, "maxTokens": 98304, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/zai-org/glm-4.5", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 131072, "max_output_tokens": 98304, "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token_cache_hit": 1.1e-7, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/zai-org-glm-4.5" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "novita/novita/qwen/qwen3-235b-a22b-thinking-2507", "slug": "novita-novita-qwen-qwen3-235b-a22b-thinking-2507", "provider": "novita", "providerSlug": "novita", "name": "qwen3-235b-a22b-thinking-2507", "displayName": "qwen3-235b-a22b-thinking-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.000003 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-235b-a22b-thinking-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-235b-a22b-thinking-2507" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/meta-llama/llama-3.1-8b-instruct", "slug": "novita-novita-meta-llama-llama-3-1-8b-instruct", "provider": "novita", "providerSlug": "novita", "name": "llama-3.1-8b-instruct", "displayName": "llama-3.1-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": 0.049999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 5e-8 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 16384, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/meta-llama/llama-3.1-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/meta-llama-llama-3.1-8b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "novita/novita/google/gemma-3-12b-it", "slug": "novita-novita-google-gemma-3-12b-it", "provider": "novita", "providerSlug": "novita", "name": "gemma-3-12b-it", "displayName": "gemma-3-12b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.09999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/google/gemma-3-12b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7, "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/google-gemma-3-12b-it" ], "manual_model_modalities_note": "Novita model detail lists text and image input with text output." }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "novita/novita/zai-org/glm-4.5v", "slug": "novita-novita-zai-org-glm-4-5v", "provider": "novita", "providerSlug": "novita", "name": "glm-4.5v", "displayName": "glm-4.5v", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 1.7999999999999998, "cachedInputUsdPer1MTokens": 0.11, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token_cache_hit": 1.1e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 65536, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/zai-org/glm-4.5v", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 65536, "max_output_tokens": 16384, "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token_cache_hit": 1.1e-7, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/zai-org-glm-4.5v" ], "manual_model_modalities_note": "Novita model detail lists text, video, and image input with text output." }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "novita/novita/openai/gpt-oss-20b", "slug": "novita-novita-openai-gpt-oss-20b", "provider": "novita", "providerSlug": "novita", "name": "gpt-oss-20b", "displayName": "gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/openai/gpt-oss-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 4e-8, "output_cost_per_token": 1.5e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/openai-gpt-oss-20b" ], "manual_model_modalities_note": "Novita model detail lists text and image input with text output." }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "novita/novita/qwen/qwen3-235b-a22b-instruct-2507", "slug": "novita-novita-qwen-qwen3-235b-a22b-instruct-2507", "provider": "novita", "providerSlug": "novita", "name": "qwen3-235b-a22b-instruct-2507", "displayName": "qwen3-235b-a22b-instruct-2507", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.58, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 5.8e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 131072, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-235b-a22b-instruct-2507", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 9e-8, "output_cost_per_token": 5.8e-7, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-235b-a22b-instruct-2507" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/deepseek/deepseek-r1-distill-qwen-14b", "slug": "novita-novita-deepseek-deepseek-r1-distill-qwen-14b", "provider": "novita", "providerSlug": "novita", "name": "deepseek-r1-distill-qwen-14b", "displayName": "deepseek-r1-distill-qwen-14b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 32768, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-r1-distill-qwen-14b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 32768, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/deepseek-deepseek-r1-distill-qwen-14b" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "novita/novita/meta-llama/llama-3.3-70b-instruct", "slug": "novita-novita-meta-llama-llama-3-3-70b-instruct", "provider": "novita", "providerSlug": "novita", "name": "llama-3.3-70b-instruct", "displayName": "llama-3.3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.135, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.135, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.35e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 120000, "maxInputTokens": 131072, "maxOutputTokens": 120000, "maxTokens": 120000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/meta-llama/llama-3.3-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.35e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 120000, "max_tokens": 120000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/meta-llama-llama-3.3-70b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_179": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_180": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "gpqadiamondcot_acc_llama3370binstruct_officialmodelcard_181": { "label": "GPQA Diamond", "category": "science", "score": 50.5, "scoreText": "50.5", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "humaneval_pass1_llama3370binstruct_officialmodelcard_182": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "mathcot_sympyintersectionscore_llama3370binstruct_officialmodelcard_183": { "label": "MATH (CoT)", "category": "math", "score": 77, "scoreText": "77.0", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 3.3 model card; used the 70B Instruct column in the instruction-tuned benchmark table." }, "local_mmlucot_macroavgacc_llama3370binstruct_officialmodelcard_9": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 86, "scoreText": "86.0", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_mmluprocot_macroavgacc_llama3370binstruct_officialmodelcard_10": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 68.9, "scoreText": "68.9", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_ifeval_llama3370binstruct_officialmodelcard_11": { "label": "IFEval", "category": "reasoning", "score": 92.1, "scoreText": "92.1", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." }, "local_humaneval_pass1_llama3370binstruct_officialmodelcard_12": { "label": "HumanEval", "category": "coding", "score": 88.4, "scoreText": "88.4", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.3", "exactModelOrSnapshot": "Llama-3.3 70B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.3 benchmark comparison table." } } }, { "id": "novita/novita/qwen/qwen-2.5-72b-instruct", "slug": "novita-novita-qwen-qwen-2-5-72b-instruct", "provider": "novita", "providerSlug": "novita", "name": "qwen-2.5-72b-instruct", "displayName": "qwen-2.5-72b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.38, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.38, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.8e-7, "output_cost_per_token": 4e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen-2.5-72b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3.8e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 32000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen-2.5-72b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." } } }, { "id": "novita/novita/mistralai/mistral-nemo", "slug": "novita-novita-mistralai-mistral-nemo", "provider": "novita", "providerSlug": "novita", "name": "mistral-nemo", "displayName": "mistral-nemo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.16999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 1.7e-7 } }, "limits": { "contextWindow": 16000, "maxInputTokens": 60288, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/mistralai/mistral-nemo", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 4e-8, "output_cost_per_token": 1.7e-7, "max_input_tokens": 60288, "max_output_tokens": 16000, "max_tokens": 16000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/mistralai-mistral-nemo" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_mistralnemo12bmainbenchmarks_hellaswag0shot_mistralaimistralnemobase2407_officialmodelcard_118": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 83.5, "scoreText": "83.5%", "metric": "HellaSwag (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_winogrande0shot_mistralaimistralnemobase2407_officialmodelcard_119": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 76.8, "scoreText": "76.8%", "metric": "Winogrande (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_openbookqa0shot_mistralaimistralnemobase2407_officialmodelcard_120": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 60.6, "scoreText": "60.6%", "metric": "OpenBookQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_commonsenseqa0shot_mistralaimistralnemobase2407_officialmodelcard_121": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 70.4, "scoreText": "70.4%", "metric": "CommonSenseQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_truthfulqa0shot_mistralaimistralnemobase2407_officialmodelcard_122": { "label": "Mistral Nemo 12B main benchmarks", "category": "safety", "score": 50.3, "scoreText": "50.3%", "metric": "TruthfulQA (0-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_mmlu5shot_mistralaimistralnemobase2407_officialmodelcard_123": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 68, "scoreText": "68.0%", "metric": "MMLU (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_triviaqa5shot_mistralaimistralnemobase2407_officialmodelcard_124": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 73.8, "scoreText": "73.8%", "metric": "TriviaQA (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." }, "local_mistralnemo12bmainbenchmarks_naturalquestions5shot_mistralaimistralnemobase2407_officialmodelcard_125": { "label": "Mistral Nemo 12B main benchmarks", "category": "general_knowledge", "score": 31.2, "scoreText": "31.2%", "metric": "NaturalQuestions (5-shot)", "higherIsBetter": true, "source_url": "https://huggingface.co/mistralai/Mistral-Nemo-Base-2407", "checked_at": "2026-05-31", "baseModelFamily": "Mistral Nemo", "exactModelOrSnapshot": "mistralai/Mistral-Nemo-Base-2407", "modelDeveloper": "Mistral AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the official HF model card benchmark table." } } }, { "id": "novita/novita/minimaxai/minimax-m1-80k", "slug": "novita-novita-minimaxai-minimax-m1-80k", "provider": "novita", "providerSlug": "novita", "name": "minimax-m1-80k", "displayName": "minimax-m1-80k", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.55, "outputUsdPer1MTokens": 2.2, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.55, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022 } }, "limits": { "contextWindow": 40000, "maxInputTokens": 1000000, "maxOutputTokens": 40000, "maxTokens": 40000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/minimaxai/minimax-m1-80k", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 1000000, "max_output_tokens": 40000, "max_tokens": 40000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/minimaxai-minimax-m1-80k" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/deepseek/deepseek-r1-0528", "slug": "novita-novita-deepseek-deepseek-r1-0528", "provider": "novita", "providerSlug": "novita", "name": "deepseek-r1-0528", "displayName": "deepseek-r1-0528", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.35, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025, "cache_read_input_token_cost": 3.5e-7, "input_cost_per_token_cache_hit": 3.5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 163840, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-r1-0528", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 3.5e-7, "input_cost_per_token_cache_hit": 3.5e-7, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/deepseek-deepseek-r1-0528" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "novita/novita/deepseek/deepseek-r1-distill-qwen-32b", "slug": "novita-novita-deepseek-deepseek-r1-distill-qwen-32b", "provider": "novita", "providerSlug": "novita", "name": "deepseek-r1-distill-qwen-32b", "displayName": "deepseek-r1-distill-qwen-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 64000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-r1-distill-qwen-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 64000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/deepseek-deepseek-r1-distill-qwen-32b" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "novita/novita/meta-llama/llama-3-8b-instruct", "slug": "novita-novita-meta-llama-llama-3-8b-instruct", "provider": "novita", "providerSlug": "novita", "name": "llama-3-8b-instruct", "displayName": "llama-3-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.04, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/meta-llama/llama-3-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/meta-llama-llama-3-8b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/microsoft/wizardlm-2-8x22b", "slug": "novita-novita-microsoft-wizardlm-2-8x22b", "provider": "novita", "providerSlug": "novita", "name": "wizardlm-2-8x22b", "displayName": "wizardlm-2-8x22b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.62, "outputUsdPer1MTokens": 0.62, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.62, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6.2e-7, "output_cost_per_token": 6.2e-7 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 65535, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/microsoft/wizardlm-2-8x22b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6.2e-7, "output_cost_per_token": 6.2e-7, "max_input_tokens": 65535, "max_output_tokens": 8000, "max_tokens": 8000, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/microsoft-wizardlm-2-8x22b" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/deepseek/deepseek-r1-0528-qwen3-8b", "slug": "novita-novita-deepseek-deepseek-r1-0528-qwen3-8b", "provider": "novita", "providerSlug": "novita", "name": "deepseek-r1-0528-qwen3-8b", "displayName": "deepseek-r1-0528-qwen3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.09, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 9e-8 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 128000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-r1-0528-qwen3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-8, "output_cost_per_token": 9e-8, "max_input_tokens": 128000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/deepseek-deepseek-r1-0528-qwen3-8b" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_pass1_deepseekr10528_officialmodelcard_149": { "label": "GPQA Diamond", "category": "reasoning", "score": 81, "scoreText": "81.0", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "sweverified_resolved_deepseekr10528_officialmodelcard_150": { "label": "SWE-bench Verified", "category": "coding", "score": 57.6, "scoreText": "57.6", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "aime2025_pass1_deepseekr10528_officialmodelcard_151": { "label": "AIME 2025", "category": "math", "score": 87.5, "scoreText": "87.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1-0528", "exactModelOrSnapshot": "DeepSeek-R1-0528", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the second column of the two-column comparison table." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "novita/novita/deepseek/deepseek-r1-distill-llama-70b", "slug": "novita-novita-deepseek-deepseek-r1-distill-llama-70b", "provider": "novita", "providerSlug": "novita", "name": "deepseek-r1-distill-llama-70b", "displayName": "deepseek-r1-distill-llama-70b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-r1-distill-llama-70b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/deepseek-deepseek-r1-distill-llama-70b" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "novita/novita/meta-llama/llama-3-70b-instruct", "slug": "novita-novita-meta-llama-llama-3-70b-instruct", "provider": "novita", "providerSlug": "novita", "name": "llama-3-70b-instruct", "displayName": "llama-3-70b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.51, "outputUsdPer1MTokens": 0.74, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.51, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5.1e-7, "output_cost_per_token": 7.4e-7 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 8192, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/meta-llama/llama-3-70b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5.1e-7, "output_cost_per_token": 7.4e-7, "max_input_tokens": 8192, "max_output_tokens": 8000, "max_tokens": 8000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/meta-llama-llama-3-70b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/qwen/qwen3-235b-a22b-fp8", "slug": "novita-novita-qwen-qwen3-235b-a22b-fp8", "provider": "novita", "providerSlug": "novita", "name": "qwen3-235b-a22b-fp8", "displayName": "qwen3-235b-a22b-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 20000, "maxInputTokens": 40960, "maxOutputTokens": 20000, "maxTokens": 20000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-235b-a22b-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 40960, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/qwen-qwen3-235b-a22b-fp8" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "slug": "novita-novita-meta-llama-llama-4-maverick-17b-128e-instruct-fp8", "provider": "novita", "providerSlug": "novita", "name": "llama-4-maverick-17b-128e-instruct-fp8", "displayName": "llama-4-maverick-17b-128e-instruct-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.27, "outputUsdPer1MTokens": 0.85, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.27, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 8.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.7e-7, "output_cost_per_token": 8.5e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "supports_vision": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/meta-llama-llama-4-maverick-17b-128e-instruct-fp8" ], "manual_model_modalities_note": "Novita model detail lists text and image input with text output." }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "novita/novita/meta-llama/llama-4-scout-17b-16e-instruct", "slug": "novita-novita-meta-llama-llama-4-scout-17b-16e-instruct", "provider": "novita", "providerSlug": "novita", "name": "llama-4-scout-17b-16e-instruct", "displayName": "llama-4-scout-17b-16e-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.18, "outputUsdPer1MTokens": 0.59, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.18, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 5.9e-7 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/meta-llama/llama-4-scout-17b-16e-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.8e-7, "output_cost_per_token": 5.9e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_vision": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/meta-llama-llama-4-scout-17b-16e-instruct" ], "manual_model_modalities_note": "Novita model detail lists text and image input with text output." }, "benchmarks": { "mmmu_accuracy_llama4maverick_officialmodelcard_184": { "label": "MMMU", "category": "multimodal", "score": 73.4, "scoreText": "73.4", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "chartqa_relaxedaccuracy_llama4maverick_officialmodelcard_185": { "label": "ChartQA", "category": "multimodal", "score": 90, "scoreText": "90.0", "metric": "relaxed_accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "docvqatest_anls_llama4maverick_officialmodelcard_186": { "label": "DocVQA", "category": "multimodal", "score": 94.4, "scoreText": "94.4", "metric": "anls", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "mmlupro_macroavgacc_llama4maverick_officialmodelcard_187": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 80.5, "scoreText": "80.5", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "gpqadiamond_accuracy_llama4maverick_officialmodelcard_188": { "label": "GPQA Diamond", "category": "science", "score": 69.8, "scoreText": "69.8", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E", "checked_at": "2026-05-31", "baseModelFamily": "Llama 4", "exactModelOrSnapshot": "Llama 4 Maverick", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Llama 4 model card; used the instruction-tuned Maverick column." }, "local_artificialanalysisintelligenceindex_score_metallamallama4maverick_benchmarkleaderboard_313": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.4, "scoreText": "18.4", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysiscodingindex_score_metallamallama4maverick_benchmarkleaderboard_314": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.6, "scoreText": "15.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." }, "local_artificialanalysisagenticindex_score_metallamallama4maverick_benchmarkleaderboard_315": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 7.2, "scoreText": "7.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/meta-llama/llama-4-maverick/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "llama-4", "exactModelOrSnapshot": "meta-llama/llama-4-maverick", "modelDeveloper": "Meta", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page; provider examples in search snippets include DeepInfra, NovitaAI, Parasail, Google Vertex, and Together." } } }, { "id": "novita/novita/nousresearch/hermes-2-pro-llama-3-8b", "slug": "novita-novita-nousresearch-hermes-2-pro-llama-3-8b", "provider": "novita", "providerSlug": "novita", "name": "hermes-2-pro-llama-3-8b", "displayName": "hermes-2-pro-llama-3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.14, "outputUsdPer1MTokens": 0.14, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.14, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 1.4e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/nousresearch/hermes-2-pro-llama-3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.4e-7, "output_cost_per_token": 1.4e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/nousresearch-hermes-2-pro-llama-3-8b" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/qwen/qwen2.5-vl-72b-instruct", "slug": "novita-novita-qwen-qwen2-5-vl-72b-instruct", "provider": "novita", "providerSlug": "novita", "name": "qwen2.5-vl-72b-instruct", "displayName": "qwen2.5-vl-72b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7999999999999999, "outputUsdPer1MTokens": 0.7999999999999999, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen2.5-vl-72b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/qwen-qwen2.5-vl-72b-instruct", "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct" ], "manual_model_modalities_note": "Novita model detail lists text, image, and video input with text output." }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_mmmu_score_qwen25vl32b_officialmodelcard_374": { "label": "MMMU", "category": "multimodal", "score": 70, "scoreText": "70", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mmmupro_score_qwen25vl32b_officialmodelcard_375": { "label": "MMMU-Pro", "category": "multimodal", "score": 49.5, "scoreText": "49.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mmstar_score_qwen25vl32b_officialmodelcard_376": { "label": "MMStar", "category": "multimodal", "score": 69.5, "scoreText": "69.5", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mathvista_score_qwen25vl32b_officialmodelcard_377": { "label": "MathVista", "category": "multimodal", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_mathvision_score_qwen25vl32b_officialmodelcard_378": { "label": "MathVision", "category": "multimodal", "score": 40, "scoreText": "40.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_ccocr_score_qwen25vl32b_officialmodelcard_379": { "label": "CC-OCR", "category": "multimodal", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_docvqa_score_qwen25vl32b_officialmodelcard_380": { "label": "DocVQA", "category": "multimodal", "score": 94.8, "scoreText": "94.8", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." }, "local_infovqa_score_qwen25vl32b_officialmodelcard_381": { "label": "InfoVQA", "category": "multimodal", "score": 83.4, "scoreText": "83.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-VL", "exactModelOrSnapshot": "Qwen2.5-VL-32B", "modelDeveloper": "Alibaba Qwen Team", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official comparison table on the 32B card." } } }, { "id": "novita/novita/sao10k/l3-70b-euryale-v2.1", "slug": "novita-novita-sao10k-l3-70b-euryale-v2-1", "provider": "novita", "providerSlug": "novita", "name": "l3-70b-euryale-v2.1", "displayName": "l3-70b-euryale-v2.1", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.48, "outputUsdPer1MTokens": 1.48, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.48, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000148, "output_cost_per_token": 0.00000148 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/sao10k/l3-70b-euryale-v2.1", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 0.00000148, "output_cost_per_token": 0.00000148, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/sao10k-l3-70b-euryale-v2.1" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/baidu/ernie-4.5-21B-a3b-thinking", "slug": "novita-novita-baidu-ernie-4-5-21b-a3b-thinking", "provider": "novita", "providerSlug": "novita", "name": "ernie-4.5-21B-a3b-thinking", "displayName": "ernie-4.5-21B-a3b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 131072, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/baidu/ernie-4.5-21B-a3b-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/baidu-ernie-4.5-21B-a3b-thinking" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/sao10k/l3-8b-lunaris", "slug": "novita-novita-sao10k-l3-8b-lunaris", "provider": "novita", "providerSlug": "novita", "name": "l3-8b-lunaris", "displayName": "l3-8b-lunaris", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.049999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 5e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/sao10k/l3-8b-lunaris", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/sao10k-l3-8b-lunaris" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/baichuan/baichuan-m2-32b", "slug": "novita-novita-baichuan-baichuan-m2-32b", "provider": "novita", "providerSlug": "novita", "name": "baichuan-m2-32b", "displayName": "baichuan-m2-32b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.07, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 7e-8 } }, "limits": { "contextWindow": 131072, "maxInputTokens": 131072, "maxOutputTokens": 131072, "maxTokens": 131072, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/baichuan/baichuan-m2-32b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-8, "output_cost_per_token": 7e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/baichuan-baichuan-m2-32b" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/baidu/ernie-4.5-vl-424b-a47b", "slug": "novita-novita-baidu-ernie-4-5-vl-424b-a47b", "provider": "novita", "providerSlug": "novita", "name": "ernie-4.5-vl-424b-a47b", "displayName": "ernie-4.5-vl-424b-a47b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.42, "outputUsdPer1MTokens": 1.25, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.42, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4.2e-7, "output_cost_per_token": 0.00000125 } }, "limits": { "contextWindow": 16000, "maxInputTokens": 123000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/baidu/ernie-4.5-vl-424b-a47b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 4.2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 123000, "max_output_tokens": 16000, "max_tokens": 16000, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/baidu-ernie-4.5-vl-424b-a47b" ], "manual_model_modalities_note": "Novita model detail lists text and image input with text output." } }, { "id": "novita/novita/baidu/ernie-4.5-300b-a47b-paddle", "slug": "novita-novita-baidu-ernie-4-5-300b-a47b-paddle", "provider": "novita", "providerSlug": "novita", "name": "ernie-4.5-300b-a47b-paddle", "displayName": "ernie-4.5-300b-a47b-paddle", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.28, "outputUsdPer1MTokens": 1.1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.28, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.8e-7, "output_cost_per_token": 0.0000011 } }, "limits": { "contextWindow": 12000, "maxInputTokens": 123000, "maxOutputTokens": 12000, "maxTokens": 12000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/baidu/ernie-4.5-300b-a47b-paddle", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.8e-7, "output_cost_per_token": 0.0000011, "max_input_tokens": 123000, "max_output_tokens": 12000, "max_tokens": 12000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/baidu-ernie-4.5-300b-a47b-paddle" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/deepseek/deepseek-prover-v2-671b", "slug": "novita-novita-deepseek-deepseek-prover-v2-671b", "provider": "novita", "providerSlug": "novita", "name": "deepseek-prover-v2-671b", "displayName": "deepseek-prover-v2-671b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 160000, "maxInputTokens": 160000, "maxOutputTokens": 160000, "maxTokens": 160000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-prover-v2-671b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 160000, "max_output_tokens": 160000, "max_tokens": 160000, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/deepseek-deepseek-prover-v2-671b" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "minif2ftest_passratio_deepseekproverv2671b_officialmodelcard_152": { "label": "MiniF2F-test", "category": "science", "score": 88.9, "scoreText": "88.9%", "metric": "Pass ratio", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-671B", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Prover-V2", "exactModelOrSnapshot": "DeepSeek-Prover-V2-671B", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; score is stated directly in prose." }, "putnambench_solvedproblems_deepseekproverv2671b_officialmodelcard_153": { "label": "PutnamBench", "category": "science", "score": null, "scoreText": "49 out of 658", "metric": "Solved problems", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-671B", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Prover-V2", "exactModelOrSnapshot": "DeepSeek-Prover-V2-671B", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; raw count is stated directly in prose and is not normalized." } } }, { "id": "novita/novita/qwen/qwen3-32b-fp8", "slug": "novita-novita-qwen-qwen3-32b-fp8", "provider": "novita", "providerSlug": "novita", "name": "qwen3-32b-fp8", "displayName": "qwen3-32b-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.44999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 4.5e-7 } }, "limits": { "contextWindow": 20000, "maxInputTokens": 40960, "maxOutputTokens": 20000, "maxTokens": 20000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-32b-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1e-7, "output_cost_per_token": 4.5e-7, "max_input_tokens": 40960, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/qwen-qwen3-32b-fp8" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/qwen/qwen3-30b-a3b-fp8", "slug": "novita-novita-qwen-qwen3-30b-a3b-fp8", "provider": "novita", "providerSlug": "novita", "name": "qwen3-30b-a3b-fp8", "displayName": "qwen3-30b-a3b-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.44999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 4.5e-7 } }, "limits": { "contextWindow": 20000, "maxInputTokens": 40960, "maxOutputTokens": 20000, "maxTokens": 20000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-30b-a3b-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 9e-8, "output_cost_per_token": 4.5e-7, "max_input_tokens": 40960, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/qwen-qwen3-30b-a3b-fp8" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/google/gemma-3-27b-it", "slug": "novita-novita-google-gemma-3-27b-it", "provider": "novita", "providerSlug": "novita", "name": "gemma-3-27b-it", "displayName": "gemma-3-27b-it", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.119, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.119, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.19e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 98304, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true, "system_messages": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/google/gemma-3-27b-it", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.19e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 98304, "max_output_tokens": 16384, "max_tokens": 16384, "supports_vision": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/google-gemma-3-27b-it" ], "manual_model_modalities_note": "Novita model detail lists text and image input with text output." }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "novita/novita/deepseek/deepseek-v3-turbo", "slug": "novita-novita-deepseek-deepseek-v3-turbo", "provider": "novita", "providerSlug": "novita", "name": "deepseek-v3-turbo", "displayName": "deepseek-v3-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39999999999999997, "outputUsdPer1MTokens": 1.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39999999999999997, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000013 } }, "limits": { "contextWindow": 16000, "maxInputTokens": 64000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-v3-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000013, "max_input_tokens": 64000, "max_output_tokens": 16000, "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/deepseek-deepseek-v3-turbo" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "mmlu_em_deepseekv3_officialmodelcard_140": { "label": "MMLU", "category": "general_knowledge", "score": 88.5, "scoreText": "88.5", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "gpqadiamond_pass1_deepseekv3_officialmodelcard_141": { "label": "GPQA Diamond", "category": "reasoning", "score": 59.1, "scoreText": "59.1", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1_deepseekv3_officialmodelcard_142": { "label": "LiveCodeBench", "category": "coding", "score": 37.6, "scoreText": "37.6", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekv3_officialmodelcard_143": { "label": "AIME 2024", "category": "math", "score": 39.2, "scoreText": "39.2", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_em_deepseekv3_officialmodelcard_144": { "label": "MATH-500", "category": "math", "score": 90.2, "scoreText": "90.2", "metric": "EM", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-V3", "exactModelOrSnapshot": "DeepSeek-V3", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." } } }, { "id": "novita/novita/deepseek/deepseek-r1-turbo", "slug": "novita-novita-deepseek-deepseek-r1-turbo", "provider": "novita", "providerSlug": "novita", "name": "deepseek-r1-turbo", "displayName": "deepseek-r1-turbo", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.7, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.7, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 16000, "maxInputTokens": 64000, "maxOutputTokens": 16000, "maxTokens": 16000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/deepseek/deepseek-r1-turbo", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 64000, "max_output_tokens": 16000, "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/deepseek-deepseek-r1-turbo" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "novita/novita/Sao10K/L3-8B-Stheno-v3.2", "slug": "novita-novita-sao10k-l3-8b-stheno-v3-2", "provider": "novita", "providerSlug": "novita", "name": "L3-8B-Stheno-v3.2", "displayName": "L3-8B-Stheno-v3.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.049999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 5e-8 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 8192, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/Sao10K/L3-8B-Stheno-v3.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 8192, "max_output_tokens": 32000, "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/Sao10K-L3-8B-Stheno-v3.2" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/gryphe/mythomax-l2-13b", "slug": "novita-novita-gryphe-mythomax-l2-13b", "provider": "novita", "providerSlug": "novita", "name": "mythomax-l2-13b", "displayName": "mythomax-l2-13b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09, "outputUsdPer1MTokens": 0.09, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 9e-8, "output_cost_per_token": 9e-8 } }, "limits": { "contextWindow": 3200, "maxInputTokens": 4096, "maxOutputTokens": 3200, "maxTokens": 3200, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/gryphe/mythomax-l2-13b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 9e-8, "output_cost_per_token": 9e-8, "max_input_tokens": 4096, "max_output_tokens": 3200, "max_tokens": 3200, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/gryphe-mythomax-l2-13b" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/baidu/ernie-4.5-vl-28b-a3b-thinking", "slug": "novita-novita-baidu-ernie-4-5-vl-28b-a3b-thinking", "provider": "novita", "providerSlug": "novita", "name": "ernie-4.5-vl-28b-a3b-thinking", "displayName": "ernie-4.5-vl-28b-a3b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.39, "outputUsdPer1MTokens": 0.39, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.39, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.9e-7, "output_cost_per_token": 3.9e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 131072, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/baidu/ernie-4.5-vl-28b-a3b-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3.9e-7, "output_cost_per_token": 3.9e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/baidu-ernie-4.5-vl-28b-a3b-thinking" ], "manual_model_modalities_note": "Novita model detail lists multimodal input with text output." } }, { "id": "novita/novita/qwen/qwen3-vl-8b-instruct", "slug": "novita-novita-qwen-qwen3-vl-8b-instruct", "provider": "novita", "providerSlug": "novita", "name": "qwen3-vl-8b-instruct", "displayName": "qwen3-vl-8b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 5e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-vl-8b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 8e-8, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-vl-8b-instruct" ], "manual_model_modalities_note": "Novita model detail lists multimodal input with text output." } }, { "id": "novita/novita/zai-org/glm-4.5-air", "slug": "novita-novita-zai-org-glm-4-5-air", "provider": "novita", "providerSlug": "novita", "name": "glm-4.5-air", "displayName": "glm-4.5-air", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.13, "outputUsdPer1MTokens": 0.85, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.13, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 8.5e-7 } }, "limits": { "contextWindow": 98304, "maxInputTokens": 131072, "maxOutputTokens": 98304, "maxTokens": 98304, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/zai-org/glm-4.5-air", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.3e-7, "output_cost_per_token": 8.5e-7, "max_input_tokens": 131072, "max_output_tokens": 98304, "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/zai-org-glm-4.5-air" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "taubench_pass1_glm45_paper_162": { "label": "TAU-Bench", "category": "agentic", "score": 70.1, "scoreText": "70.1%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "aime24_pass1_glm45_paper_163": { "label": "AIME 2024", "category": "math", "score": 91, "scoreText": "91.0%", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "swebenchverified_resolved_glm45_paper_164": { "label": "SWE-bench Verified", "category": "coding", "score": 64.2, "scoreText": "64.2%", "metric": "Resolved", "higherIsBetter": true, "source_url": "https://arxiv.org/abs/2508.06471", "checked_at": "2026-05-31", "baseModelFamily": "GLM-4.5", "exactModelOrSnapshot": "GLM-4.5", "modelDeveloper": "Zhipu AI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "ArXiv abstract states the headline benchmark scores directly." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "novita/novita/qwen/qwen3-vl-30b-a3b-instruct", "slug": "novita-novita-qwen-qwen3-vl-30b-a3b-instruct", "provider": "novita", "providerSlug": "novita", "name": "qwen3-vl-30b-a3b-instruct", "displayName": "qwen3-vl-30b-a3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 0.7, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 7e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-vl-30b-a3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-vl-30b-a3b-instruct" ], "manual_model_modalities_note": "Novita model detail lists multimodal input with text output." } }, { "id": "novita/novita/qwen/qwen3-vl-30b-a3b-thinking", "slug": "novita-novita-qwen-qwen3-vl-30b-a3b-thinking", "provider": "novita", "providerSlug": "novita", "name": "qwen3-vl-30b-a3b-thinking", "displayName": "qwen3-vl-30b-a3b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.19999999999999998, "outputUsdPer1MTokens": 1, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.19999999999999998, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000001 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "image", "text", "video" ], "input": [ "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-vl-30b-a3b-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-vl-30b-a3b-thinking" ], "manual_model_modalities_note": "Novita model detail lists multimodal input with text output." } }, { "id": "novita/novita/qwen/qwen3-omni-30b-a3b-thinking", "slug": "novita-novita-qwen-qwen3-omni-30b-a3b-thinking", "provider": "novita", "providerSlug": "novita", "name": "qwen3-omni-30b-a3b-thinking", "displayName": "qwen3-omni-30b-a3b-thinking", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.9700000000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 9.7e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 65536, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true, "reasoning": true, "audio_input": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-omni-30b-a3b-thinking", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.5e-7, "output_cost_per_token": 9.7e-7, "max_input_tokens": 65536, "max_output_tokens": 16384, "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "supports_audio_input": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-omni-30b-a3b-thinking" ], "manual_model_modalities_note": "Novita model detail lists text, audio, video, and image input with text and audio output." } }, { "id": "novita/novita/qwen/qwen3-omni-30b-a3b-instruct", "slug": "novita-novita-qwen-qwen3-omni-30b-a3b-instruct", "provider": "novita", "providerSlug": "novita", "name": "qwen3-omni-30b-a3b-instruct", "displayName": "qwen3-omni-30b-a3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.9700000000000001, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 9.7e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 65536, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "response_schema": true, "audio_input": true, "audio_output": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-omni-30b-a3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.5e-7, "output_cost_per_token": 9.7e-7, "max_input_tokens": 65536, "max_output_tokens": 16384, "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "supports_audio_input": true, "supports_audio_output": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-omni-30b-a3b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text, audio, video, and image input with text and audio output." } }, { "id": "novita/novita/qwen/qwen-mt-plus", "slug": "novita-novita-qwen-qwen-mt-plus", "provider": "novita", "providerSlug": "novita", "name": "qwen-mt-plus", "displayName": "qwen-mt-plus", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.25, "outputUsdPer1MTokens": 0.75, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 16384, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen-mt-plus", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7.5e-7, "max_input_tokens": 16384, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen-mt-plus" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/baidu/ernie-4.5-vl-28b-a3b", "slug": "novita-novita-baidu-ernie-4-5-vl-28b-a3b", "provider": "novita", "providerSlug": "novita", "name": "ernie-4.5-vl-28b-a3b", "displayName": "ernie-4.5-vl-28b-a3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.14, "outputUsdPer1MTokens": 0.56, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.14, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 5.6e-7 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 30000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "vision": true, "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/baidu/ernie-4.5-vl-28b-a3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.4e-7, "output_cost_per_token": 5.6e-7, "max_input_tokens": 30000, "max_output_tokens": 8000, "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/baidu-ernie-4.5-vl-28b-a3b" ], "manual_model_modalities_note": "Novita model detail lists text and image input with text output." } }, { "id": "novita/novita/baidu/ernie-4.5-21B-a3b", "slug": "novita-novita-baidu-ernie-4-5-21b-a3b", "provider": "novita", "providerSlug": "novita", "name": "ernie-4.5-21B-a3b", "displayName": "ernie-4.5-21B-a3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.28, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 120000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/baidu/ernie-4.5-21B-a3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7, "max_input_tokens": 120000, "max_output_tokens": 8000, "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/baidu-ernie-4.5-21B-a3b" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/qwen/qwen3-8b-fp8", "slug": "novita-novita-qwen-qwen3-8b-fp8", "provider": "novita", "providerSlug": "novita", "name": "qwen3-8b-fp8", "displayName": "qwen3-8b-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.035, "outputUsdPer1MTokens": 0.13799999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.035, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.38e-7 } }, "limits": { "contextWindow": 20000, "maxInputTokens": 128000, "maxOutputTokens": 20000, "maxTokens": 20000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-8b-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.38e-7, "max_input_tokens": 128000, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/qwen-qwen3-8b-fp8" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/qwen/qwen3-4b-fp8", "slug": "novita-novita-qwen-qwen3-4b-fp8", "provider": "novita", "providerSlug": "novita", "name": "qwen3-4b-fp8", "displayName": "qwen3-4b-fp8", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.03, "outputUsdPer1MTokens": 0.03, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.03, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-8, "output_cost_per_token": 3e-8 } }, "limits": { "contextWindow": 20000, "maxInputTokens": 128000, "maxOutputTokens": 20000, "maxTokens": 20000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "system_messages": true, "reasoning": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-4b-fp8", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-8, "output_cost_per_token": 3e-8, "max_input_tokens": 128000, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/qwen-qwen3-4b-fp8" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/qwen/qwen2.5-7b-instruct", "slug": "novita-novita-qwen-qwen2-5-7b-instruct", "provider": "novita", "providerSlug": "novita", "name": "qwen2.5-7b-instruct", "displayName": "qwen2.5-7b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": 0.07, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 7e-8 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32000, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true, "response_schema": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen2.5-7b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-8, "output_cost_per_token": 7e-8, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/qwen-qwen2.5-7b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." } } }, { "id": "novita/novita/meta-llama/llama-3.2-3b-instruct", "slug": "novita-novita-meta-llama-llama-3-2-3b-instruct", "provider": "novita", "providerSlug": "novita", "name": "llama-3.2-3b-instruct", "displayName": "llama-3.2-3b-instruct", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.03, "outputUsdPer1MTokens": 0.049999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.03, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-8, "output_cost_per_token": 5e-8 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 32768, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/meta-llama/llama-3.2-3b-instruct", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 32768, "max_output_tokens": 32000, "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models/model-detail/meta-llama-llama-3.2-3b-instruct" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "novita/novita/sao10k/l31-70b-euryale-v2.2", "slug": "novita-novita-sao10k-l31-70b-euryale-v2-2", "provider": "novita", "providerSlug": "novita", "name": "l31-70b-euryale-v2.2", "displayName": "l31-70b-euryale-v2.2", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.48, "outputUsdPer1MTokens": 1.48, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.48, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.00000148, "output_cost_per_token": 0.00000148 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "tool_choice": true, "system_messages": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/sao10k/l31-70b-euryale-v2.2", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 0.00000148, "output_cost_per_token": 0.00000148, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "manual_model_modalities_review_status": "reviewed", "manual_model_modalities_source_urls": [ "https://novita.ai/models-console/model-detail/sao10k-l31-70b-euryale-v2.2" ], "manual_model_modalities_note": "Novita model detail lists text input and text output." } }, { "id": "novita/novita/qwen/qwen3-embedding-0.6b", "slug": "novita-novita-qwen-qwen3-embedding-0-6b", "provider": "novita", "providerSlug": "novita", "name": "qwen3-embedding-0.6b", "displayName": "qwen3-embedding-0.6b", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-embedding-0.6b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "embedding", "input_cost_per_token": 7e-8, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768 }, "benchmarks": { "local_qwen3evaluationsuite_mtebr_qwen3embedding06b_officialmodelcard_352": { "label": "Qwen3 evaluation suite", "category": "other", "score": 61.82, "scoreText": "61.82", "metric": "MTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_cmtebr_qwen3embedding06b_officialmodelcard_353": { "label": "Qwen3 evaluation suite", "category": "other", "score": 71.02, "scoreText": "71.02", "metric": "CMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mmtebr_qwen3embedding06b_officialmodelcard_354": { "label": "Qwen3 evaluation suite", "category": "other", "score": 64.64, "scoreText": "64.64", "metric": "MMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mldr_qwen3embedding06b_officialmodelcard_355": { "label": "Qwen3 evaluation suite", "category": "other", "score": 50.26, "scoreText": "50.26", "metric": "MLDR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mtebcode_qwen3embedding06b_officialmodelcard_356": { "label": "Qwen3 evaluation suite", "category": "other", "score": 75.41, "scoreText": "75.41", "metric": "MTEB-Code", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_followir_qwen3embedding06b_officialmodelcard_357": { "label": "Qwen3 evaluation suite", "category": "other", "score": 5.09, "scoreText": "5.09", "metric": "FollowIR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." } } }, { "id": "novita/novita/qwen/qwen3-embedding-8b", "slug": "novita-novita-qwen-qwen3-embedding-8b", "provider": "novita", "providerSlug": "novita", "name": "qwen3-embedding-8b", "displayName": "qwen3-embedding-8b", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.07, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.07, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-embedding-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "embedding", "input_cost_per_token": 7e-8, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096 }, "benchmarks": { "local_qwen3evaluationsuite_mtebr_qwen3embedding06b_officialmodelcard_352": { "label": "Qwen3 evaluation suite", "category": "other", "score": 61.82, "scoreText": "61.82", "metric": "MTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_cmtebr_qwen3embedding06b_officialmodelcard_353": { "label": "Qwen3 evaluation suite", "category": "other", "score": 71.02, "scoreText": "71.02", "metric": "CMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mmtebr_qwen3embedding06b_officialmodelcard_354": { "label": "Qwen3 evaluation suite", "category": "other", "score": 64.64, "scoreText": "64.64", "metric": "MMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mldr_qwen3embedding06b_officialmodelcard_355": { "label": "Qwen3 evaluation suite", "category": "other", "score": 50.26, "scoreText": "50.26", "metric": "MLDR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mtebcode_qwen3embedding06b_officialmodelcard_356": { "label": "Qwen3 evaluation suite", "category": "other", "score": 75.41, "scoreText": "75.41", "metric": "MTEB-Code", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_followir_qwen3embedding06b_officialmodelcard_357": { "label": "Qwen3 evaluation suite", "category": "other", "score": 5.09, "scoreText": "5.09", "metric": "FollowIR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." } } }, { "id": "novita/novita/baai/bge-m3", "slug": "novita-novita-baai-bge-m3", "provider": "novita", "providerSlug": "novita", "name": "bge-m3", "displayName": "bge-m3", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.01, "outputUsdPer1MTokens": 0.01, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.01, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-8, "output_cost_per_token": 1e-8 } }, "limits": { "contextWindow": 96000, "maxInputTokens": 8192, "maxOutputTokens": 96000, "maxTokens": 96000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/baai/bge-m3", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "embedding", "input_cost_per_token": 1e-8, "output_cost_per_token": 1e-8, "max_input_tokens": 8192, "max_output_tokens": 96000, "max_tokens": 96000 }, "benchmarks": { "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "novita/novita/qwen/qwen3-reranker-8b", "slug": "novita-novita-qwen-qwen3-reranker-8b", "provider": "novita", "providerSlug": "novita", "name": "qwen3-reranker-8b", "displayName": "qwen3-reranker-8b", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": 0.049999999999999996, "outputUsdPer1MTokens": 0.049999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.049999999999999996, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 5e-8, "output_cost_per_token": 5e-8 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 32768, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/qwen/qwen3-reranker-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "rerank", "input_cost_per_token": 5e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "local_qwen3evaluationsuite_mtebr_qwen3reranker06b_officialmodelcard_358": { "label": "Qwen3 evaluation suite", "category": "other", "score": 65.8, "scoreText": "65.80", "metric": "MTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_cmtebr_qwen3reranker06b_officialmodelcard_359": { "label": "Qwen3 evaluation suite", "category": "other", "score": 71.31, "scoreText": "71.31", "metric": "CMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mmtebr_qwen3reranker06b_officialmodelcard_360": { "label": "Qwen3 evaluation suite", "category": "other", "score": 66.36, "scoreText": "66.36", "metric": "MMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mldr_qwen3reranker06b_officialmodelcard_361": { "label": "Qwen3 evaluation suite", "category": "other", "score": 67.28, "scoreText": "67.28", "metric": "MLDR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_mtebcode_qwen3reranker06b_officialmodelcard_362": { "label": "Qwen3 evaluation suite", "category": "other", "score": 73.42, "scoreText": "73.42", "metric": "MTEB-Code", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." }, "local_qwen3evaluationsuite_followir_qwen3reranker06b_officialmodelcard_363": { "label": "Qwen3 evaluation suite", "category": "other", "score": 5.41, "scoreText": "5.41", "metric": "FollowIR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-reranker", "exactModelOrSnapshot": "Qwen3-Reranker-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B reranker." } } }, { "id": "novita/novita/baai/bge-reranker-v2-m3", "slug": "novita-novita-baai-bge-reranker-v2-m3", "provider": "novita", "providerSlug": "novita", "name": "bge-reranker-v2-m3", "displayName": "bge-reranker-v2-m3", "mode": "rerank", "pricing": { "inputUsdPer1MTokens": 0.01, "outputUsdPer1MTokens": 0.01, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.01, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-8, "output_cost_per_token": 1e-8 } }, "limits": { "contextWindow": 8000, "maxInputTokens": 8000, "maxOutputTokens": 8000, "maxTokens": 8000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "ranking", "text" ], "input": [ "text" ], "output": [ "ranking" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "novita/baai/bge-reranker-v2-m3", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "novita", "mode": "rerank", "input_cost_per_token": 1e-8, "output_cost_per_token": 1e-8, "max_input_tokens": 8000, "max_output_tokens": 8000, "max_tokens": 8000, "manual_modalities_contract_id": "rerank", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." } } }, { "id": "llamagate/llamagate/llama-3.1-8b", "slug": "llamagate-llamagate-llama-3-1-8b", "provider": "llamagate", "providerSlug": "llamagate", "name": "llama-3.1-8b", "displayName": "llama-3.1-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.03, "outputUsdPer1MTokens": 0.049999999999999996, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.03, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-8, "output_cost_per_token": 5e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/llama-3.1-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3e-8, "output_cost_per_token": 5e-8, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "benchmarks": { "mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_174": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mmluprocot_macroavgacc_llama31405binstruct_officialmodelcard_175": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "gpqadiamondcot_acc_llama31405binstruct_officialmodelcard_176": { "label": "GPQA Diamond", "category": "science", "score": 49, "scoreText": "49.0", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "humaneval_pass1_llama31405binstruct_officialmodelcard_177": { "label": "HumanEval", "category": "coding", "score": 89, "scoreText": "89.0", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "mathcot_sympyintersectionscore_llama31405binstruct_officialmodelcard_178": { "label": "MATH (CoT)", "category": "math", "score": 73.8, "scoreText": "73.8", "metric": "sympy_intersection_score", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "HF model card table includes the 405B Instruct column; selected the rightmost 405B value." }, "local_mmlu_macroavgaccchar_llama31405b_officialmodelcard_0": { "label": "MMLU", "category": "general_knowledge", "score": 85.2, "scoreText": "85.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmluprocot_macroavgaccchar_llama31405b_officialmodelcard_1": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 61.6, "scoreText": "61.6", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_agievalenglish_averageaccchar_llama31405b_officialmodelcard_2": { "label": "AGIEval English", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6", "metric": "average/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Base-model column from the official 405B card benchmark table." }, "local_mmlu_macroavgacc_llama31405binstruct_officialmodelcard_3": { "label": "MMLU", "category": "general_knowledge", "score": 87.3, "scoreText": "87.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlucot_macroavgacc_llama31405binstruct_officialmodelcard_4": { "label": "MMLU (CoT)", "category": "general_knowledge", "score": 88.6, "scoreText": "88.6", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmluprocot_microavgaccchar_llama31405binstruct_officialmodelcard_5": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 73.3, "scoreText": "73.3", "metric": "micro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_ifeval_llama31405binstruct_officialmodelcard_6": { "label": "IFEval", "category": "reasoning", "score": 88.6, "scoreText": "88.6", "metric": "", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_arcc_acc_llama31405binstruct_officialmodelcard_7": { "label": "ARC-Challenge", "category": "reasoning", "score": 96.9, "scoreText": "96.9", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_gpqa_em_llama31405binstruct_officialmodelcard_8": { "label": "GPQA", "category": "science", "score": 50.7, "scoreText": "50.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama 3.1 405B Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned table on the official 405B card." }, "local_mmlu_macroavgacc_llama318binstruct_officialmodelcard_267": { "label": "MMLU", "category": "general_knowledge", "score": 69.4, "scoreText": "69.4%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_mmlu_macroavgacc_llama3170binstruct_officialmodelcard_268": { "label": "MMLU", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama318binstruct_officialmodelcard_269": { "label": "HumanEval", "category": "coding", "score": 72.6, "scoreText": "72.6%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_humaneval_pass1_llama3170binstruct_officialmodelcard_270": { "label": "HumanEval", "category": "coding", "score": 80.5, "scoreText": "80.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama318binstruct_officialmodelcard_271": { "label": "GSM8K (CoT)", "category": "math", "score": 84.5, "scoreText": "84.5%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_gsm8kcot_emmaj11_llama3170binstruct_officialmodelcard_272": { "label": "GSM8K (CoT)", "category": "math", "score": 95.1, "scoreText": "95.1%", "metric": "em_maj1@1", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama318binstruct_officialmodelcard_273": { "label": "BFCL", "category": "other", "score": 76.1, "scoreText": "76.1%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-8B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_bfcl_acc_llama3170binstruct_officialmodelcard_274": { "label": "BFCL", "category": "other", "score": 84.8, "scoreText": "84.8%", "metric": "acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.1", "exactModelOrSnapshot": "Llama-3.1-70B-Instruct", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-tuned evaluation table in the model card." }, "local_artificialanalysisintelligenceindex_score_metallamallama3170binstruct_thirdpartyreport_299": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 12.2, "scoreText": "12.2", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysiscodingindex_score_metallamallama3170binstruct_thirdpartyreport_300": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 10.9, "scoreText": "10.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." }, "local_artificialanalysisagenticindex_score_metallamallama3170binstruct_thirdpartyreport_301": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 5.1, "scoreText": "5.1", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/meta-llama/llama-3.1-70b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "llama-3.1", "exactModelOrSnapshot": "meta-llama/llama-3.1-70b-instruct", "modelDeveloper": "Meta", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page shows 4 providers; DeepInfra (Turbo) is visible in the route panel." } } }, { "id": "llamagate/llamagate/llama-3.2-3b", "slug": "llamagate-llamagate-llama-3-2-3b", "provider": "llamagate", "providerSlug": "llamagate", "name": "llama-3.2-3b", "displayName": "llama-3.2-3b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 131072, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/llama-3.2-3b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 4e-8, "output_cost_per_token": 8e-8, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "benchmarks": { "local_mmlu_macroavgaccchar_llama321b_officialmodelcard_13": { "label": "MMLU", "category": "general_knowledge", "score": 32.2, "scoreText": "32.2", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama321b_officialmodelcard_14": { "label": "ARC-Challenge", "category": "reasoning", "score": 32.8, "scoreText": "32.8", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama321b_officialmodelcard_15": { "label": "SQuAD", "category": "general_knowledge", "score": 49.2, "scoreText": "49.2", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgaccchar_llama323b_officialmodelcard_16": { "label": "MMLU", "category": "general_knowledge", "score": 58, "scoreText": "58", "metric": "macro_avg/acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_arcchallenge_accchar_llama323b_officialmodelcard_17": { "label": "ARC-Challenge", "category": "reasoning", "score": 69.1, "scoreText": "69.1", "metric": "acc_char", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_squad_em_llama323b_officialmodelcard_18": { "label": "SQuAD", "category": "general_knowledge", "score": 67.7, "scoreText": "67.7", "metric": "em", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 base pretrained benchmark table." }, "local_mmlu_macroavgacc_llama321bbf16_officialmodelcard_19": { "label": "MMLU", "category": "general_knowledge", "score": 49.3, "scoreText": "49.3", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama321bbf16_officialmodelcard_20": { "label": "IFEval", "category": "reasoning", "score": 59.5, "scoreText": "59.5", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 1B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_mmlu_macroavgacc_llama323bbf16_officialmodelcard_21": { "label": "MMLU", "category": "general_knowledge", "score": 63.4, "scoreText": "63.4", "metric": "macro_avg/acc", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." }, "local_ifeval_avgpromptinstructionaccloosestrict_llama323bbf16_officialmodelcard_22": { "label": "IFEval", "category": "reasoning", "score": 77.4, "scoreText": "77.4", "metric": "Avg(Prompt/Instruction acc Loose/Strict)", "higherIsBetter": true, "source_url": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct", "checked_at": "2026-05-31", "baseModelFamily": "Llama 3.2", "exactModelOrSnapshot": "Llama 3.2 3B bf16", "modelDeveloper": "Meta", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official 3.2 instruction-tuned benchmark table, bf16 column." } } }, { "id": "llamagate/llamagate/mistral-7b-v0.3", "slug": "llamagate-llamagate-mistral-7b-v0-3", "provider": "llamagate", "providerSlug": "llamagate", "name": "mistral-7b-v0.3", "displayName": "mistral-7b-v0.3", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/mistral-7b-v0.3", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1e-7, "output_cost_per_token": 1.5e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "benchmarks": { "local_mistral7bcomparisontable_ifeval0shot_mistral7b_thirdpartyreport_126": { "label": "Mistral 7B comparison table", "category": "other", "score": 49.93, "scoreText": "49.93", "metric": "IFEval 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mtbench_mistral7b_thirdpartyreport_127": { "label": "Mistral 7B comparison table", "category": "preference", "score": 7.62, "scoreText": "7.62", "metric": "MT-Bench", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_agieval5shot_mistral7b_thirdpartyreport_128": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 37.15, "scoreText": "37.15", "metric": "AGI-Eval 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlu5shot_mistral7b_thirdpartyreport_129": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 62.01, "scoreText": "62.01", "metric": "MMLU 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mmlupro5shot_mistral7b_thirdpartyreport_130": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 30.34, "scoreText": "30.34", "metric": "MMLU-Pro 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_obqa0shot_mistral7b_thirdpartyreport_131": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 47.4, "scoreText": "47.40", "metric": "OBQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_siqa0shot_mistral7b_thirdpartyreport_132": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 59.64, "scoreText": "59.64", "metric": "SIQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_hellaswag10shot_mistral7b_thirdpartyreport_133": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 84.61, "scoreText": "84.61", "metric": "HellaSwag 10-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_winogrande5shot_mistral7b_thirdpartyreport_134": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 78.85, "scoreText": "78.85", "metric": "WinoGrande 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_truthfulqa0shot_mistral7b_thirdpartyreport_135": { "label": "Mistral 7B comparison table", "category": "safety", "score": 59.68, "scoreText": "59.68", "metric": "TruthfulQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_boolq5shot_mistral7b_thirdpartyreport_136": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 87.34, "scoreText": "87.34", "metric": "BoolQ 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_squad200shot_mistral7b_thirdpartyreport_137": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 18.66, "scoreText": "18.66", "metric": "SQuAD 2.0 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_arcc25shot_mistral7b_thirdpartyreport_138": { "label": "Mistral 7B comparison table", "category": "general_knowledge", "score": 63.65, "scoreText": "63.65", "metric": "ARC-C 25-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gpqa0shot_mistral7b_thirdpartyreport_139": { "label": "Mistral 7B comparison table", "category": "science", "score": 30.45, "scoreText": "30.45", "metric": "GPQA 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_bbh3shot_mistral7b_thirdpartyreport_140": { "label": "Mistral 7B comparison table", "category": "reasoning", "score": 46.73, "scoreText": "46.73", "metric": "BBH 3-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalsynthesispass1_mistral7b_thirdpartyreport_141": { "label": "Mistral 7B comparison table", "category": "coding", "score": 34.76, "scoreText": "34.76", "metric": "HumanEvalSynthesis pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalexplainpass1_mistral7b_thirdpartyreport_142": { "label": "Mistral 7B comparison table", "category": "coding", "score": 21.65, "scoreText": "21.65", "metric": "HumanEvalExplain pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_humanevalfixpass1_mistral7b_thirdpartyreport_143": { "label": "Mistral 7B comparison table", "category": "coding", "score": 53.05, "scoreText": "53.05", "metric": "HumanEvalFix pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mbpppass1_mistral7b_thirdpartyreport_144": { "label": "Mistral 7B comparison table", "category": "coding", "score": 38.6, "scoreText": "38.60", "metric": "MBPP pass@1", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_gsm8k5shotcot_mistral7b_thirdpartyreport_145": { "label": "Mistral 7B comparison table", "category": "math", "score": 37.68, "scoreText": "37.68", "metric": "GSM8k 5-shot, cot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_math4shot_mistral7b_thirdpartyreport_146": { "label": "Mistral 7B comparison table", "category": "math", "score": 13.1, "scoreText": "13.10", "metric": "MATH 4-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_pawsx7langs0shot_mistral7b_thirdpartyreport_147": { "label": "Mistral 7B comparison table", "category": "other", "score": 56.57, "scoreText": "56.57", "metric": "PAWS-X (7 langs) 0-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." }, "local_mistral7bcomparisontable_mgsm6langs5shot_mistral7b_thirdpartyreport_148": { "label": "Mistral 7B comparison table", "category": "math", "score": 35.27, "scoreText": "35.27", "metric": "MGSM (6 langs) 5-shot", "higherIsBetter": true, "source_url": "https://developer.nvidia.com/blog/?p=90636", "checked_at": "2026-05-31", "baseModelFamily": "Mistral 7B", "exactModelOrSnapshot": "Mistral 7B", "modelDeveloper": "Mistral AI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Score taken from the NVIDIA comparison table that includes Mistral 7B." } } }, { "id": "llamagate/llamagate/qwen3-8b", "slug": "llamagate-llamagate-qwen3-8b", "provider": "llamagate", "providerSlug": "llamagate", "name": "qwen3-8b", "displayName": "qwen3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.04, "outputUsdPer1MTokens": 0.14, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.04, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 4e-8, "output_cost_per_token": 1.4e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/qwen3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 4e-8, "output_cost_per_token": 1.4e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true } }, { "id": "llamagate/llamagate/dolphin3-8b", "slug": "llamagate-llamagate-dolphin3-8b", "provider": "llamagate", "providerSlug": "llamagate", "name": "dolphin3-8b", "displayName": "dolphin3-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/dolphin3-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 8e-8, "output_cost_per_token": 1.5e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true } }, { "id": "llamagate/llamagate/deepseek-r1-8b", "slug": "llamagate-llamagate-deepseek-r1-8b", "provider": "llamagate", "providerSlug": "llamagate", "name": "deepseek-r1-8b", "displayName": "deepseek-r1-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 65536, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/deepseek-r1-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 65536, "max_output_tokens": 16384, "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_reasoning": true }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "llamagate/llamagate/deepseek-r1-7b-qwen", "slug": "llamagate-llamagate-deepseek-r1-7b-qwen", "provider": "llamagate", "providerSlug": "llamagate", "name": "deepseek-r1-7b-qwen", "displayName": "deepseek-r1-7b-qwen", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 16384, "maxInputTokens": 131072, "maxOutputTokens": 16384, "maxTokens": 16384, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/deepseek-r1-7b-qwen", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 16384, "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 8e-8, "output_cost_per_token": 1.5e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_reasoning": true }, "benchmarks": { "gpqadiamond_pass1_deepseekr1_officialmodelcard_145": { "label": "GPQA Diamond", "category": "reasoning", "score": 71.5, "scoreText": "71.5", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "livecodebench_pass1cot_deepseekr1_officialmodelcard_146": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "Pass@1-COT", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aime2024_pass1_deepseekr1_officialmodelcard_147": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "math500_pass1_deepseekr1_officialmodelcard_148": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "Pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the last column of the comparison table." }, "aiderpolyglot_percentcorrect_deepseekdeepseekreasoner_benchmarkleaderboard_226": { "label": "Aider Polyglot", "category": "coding", "score": 71.4, "scoreText": "71.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-reasoner", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for DeepSeek R1 (0528)." }, "artificialanalysisintelligenceindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_276": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysiscodingindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_277": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "artificialanalysisagenticindex_indexscore_deepseekdeepseekr1_benchmarkleaderboard_278": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek R1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "local_mmlu_pass1_deepseekr1_officialmodelcard_91": { "label": "MMLU", "category": "general_knowledge", "score": 90.8, "scoreText": "90.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_gpqadiamond_pass1_deepseekr1_officialmodelcard_92": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_livecodebenchpass1cot_pass1_deepseekr1_officialmodelcard_93": { "label": "LiveCodeBench", "category": "coding", "score": 65.9, "scoreText": "65.9", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_codeforcesrating_rating_deepseekr1_officialmodelcard_94": { "label": "Codeforces", "category": "coding", "score": 2029, "scoreText": "2029", "metric": "rating", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_sweverifiedresolved_resolved_deepseekr1_officialmodelcard_95": { "label": "SWE-bench Verified", "category": "agentic", "score": 49.2, "scoreText": "49.2", "metric": "resolved", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aiderpolyglot_accuracy_deepseekr1_officialmodelcard_96": { "label": "Aider Polyglot", "category": "coding", "score": 53.3, "scoreText": "53.3", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_aime2024_pass1_deepseekr1_officialmodelcard_97": { "label": "AIME 2024", "category": "math", "score": 79.8, "scoreText": "79.8", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_math500_pass1_deepseekr1_officialmodelcard_98": { "label": "MATH-500", "category": "math", "score": 97.3, "scoreText": "97.3", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-R1", "exactModelOrSnapshot": "DeepSeek-R1", "modelDeveloper": "DeepSeek-AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "R1 evaluation table on the official model card." }, "local_artificialanalysisintelligenceindex_score_deepseekdeepseekr1_benchmarkleaderboard_296": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 18.8, "scoreText": "18.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysiscodingindex_score_deepseekdeepseekr1_benchmarkleaderboard_297": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 15.9, "scoreText": "15.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." }, "local_artificialanalysisagenticindex_score_deepseekdeepseekr1_benchmarkleaderboard_298": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 3.8, "scoreText": "3.8", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/deepseek/deepseek-r1/benchmarks?sort=throughput", "checked_at": "2026-05-31", "baseModelFamily": "deepseek-r1", "exactModelOrSnapshot": "deepseek/deepseek-r1", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page with route-level provider context hidden behind multi-provider routing." } } }, { "id": "llamagate/llamagate/openthinker-7b", "slug": "llamagate-llamagate-openthinker-7b", "provider": "llamagate", "providerSlug": "llamagate", "name": "openthinker-7b", "displayName": "openthinker-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.08, "outputUsdPer1MTokens": 0.15, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.08, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 8e-8, "output_cost_per_token": 1.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/openthinker-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 8e-8, "output_cost_per_token": 1.5e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_reasoning": true } }, { "id": "llamagate/llamagate/qwen2.5-coder-7b", "slug": "llamagate-llamagate-qwen2-5-coder-7b", "provider": "llamagate", "providerSlug": "llamagate", "name": "qwen2.5-coder-7b", "displayName": "qwen2.5-coder-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 1.2e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/qwen2.5-coder-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 6e-8, "output_cost_per_token": 1.2e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "benchmarks": { "local_mmlu_accuracy_qwen257binstruct_officiallaunchpost_275": { "label": "MMLU", "category": "general_knowledge", "score": 74.2, "scoreText": "74.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_mmlu_accuracy_qwen2532binstruct_officiallaunchpost_276": { "label": "MMLU", "category": "general_knowledge", "score": 83.3, "scoreText": "83.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_math_accuracy_qwen257binstruct_officiallaunchpost_277": { "label": "MATH", "category": "math", "score": 49.8, "scoreText": "49.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_math_accuracy_qwen2532binstruct_officiallaunchpost_278": { "label": "MATH", "category": "math", "score": 57.7, "scoreText": "57.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_humaneval_pass1_qwen257binstruct_officiallaunchpost_279": { "label": "HumanEval", "category": "coding", "score": 57.9, "scoreText": "57.9%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-7B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-7B performance table in the launch post." }, "local_humaneval_pass1_qwen2532binstruct_officiallaunchpost_280": { "label": "HumanEval", "category": "coding", "score": 58.5, "scoreText": "58.5%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://qwenlm.github.io/blog/qwen2.5-llm/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5", "exactModelOrSnapshot": "Qwen2.5-32B-Instruct", "modelDeveloper": "Qwen", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Qwen2.5-14B/32B performance table in the launch post." }, "local_artificialanalysiscodingindex_score_qwenqwen2572binstruct_thirdpartyreport_302": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 11.9, "scoreText": "11.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_gpqadiamond_accuracy_qwenqwen2572binstruct_thirdpartyreport_303": { "label": "GPQA Diamond", "category": "reasoning", "score": 49.1, "scoreText": "49.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_hle_accuracy_qwenqwen2572binstruct_thirdpartyreport_304": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 4.2, "scoreText": "4.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_ifbench_accuracy_qwenqwen2572binstruct_thirdpartyreport_305": { "label": "IFBench", "category": "reasoning", "score": 36.9, "scoreText": "36.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_scicode_accuracy_qwenqwen2572binstruct_thirdpartyreport_306": { "label": "SciCode", "category": "coding", "score": 26.7, "scoreText": "26.7%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", "checked_at": "2026-05-31", "baseModelFamily": "qwen2.5", "exactModelOrSnapshot": "qwen/qwen-2.5-72b-instruct", "modelDeveloper": "Qwen", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter page shows DeepInfra and NovitaAI routes." }, "local_aiderpolyglot_percentcorrect_qwen25coder32binstruct_benchmarkleaderboard_247": { "label": "Aider Polyglot", "category": "agentic", "score": 16.4, "scoreText": "16.4%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "Qwen2.5-Coder", "exactModelOrSnapshot": "Qwen2.5-Coder-32B-Instruct", "modelDeveloper": "Alibaba Qwen", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider polyglot leaderboard row for the 32B instruct checkpoint." } } }, { "id": "llamagate/llamagate/deepseek-coder-6.7b", "slug": "llamagate-llamagate-deepseek-coder-6-7b", "provider": "llamagate", "providerSlug": "llamagate", "name": "deepseek-coder-6.7b", "displayName": "deepseek-coder-6.7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 1.2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/deepseek-coder-6.7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-8, "output_cost_per_token": 1.2e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "benchmarks": { "local_aidercodeeditingleaderboard_percentcorrect_deepseekcoderv20724_benchmarkleaderboard_246": { "label": "Aider Code Editing", "category": "agentic", "score": 72.9, "scoreText": "72.9%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/edit.html", "checked_at": "2026-05-31", "baseModelFamily": "DeepSeek-Coder", "exactModelOrSnapshot": "DeepSeek Coder V2 0724", "modelDeveloper": "DeepSeek", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Aider’s older code-editing leaderboard shows DeepSeek Coder V2 0724 at 72.9% with diff format." } } }, { "id": "llamagate/llamagate/codellama-7b", "slug": "llamagate-llamagate-codellama-7b", "provider": "llamagate", "providerSlug": "llamagate", "name": "codellama-7b", "displayName": "codellama-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.06, "outputUsdPer1MTokens": 0.12, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.06, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 6e-8, "output_cost_per_token": 1.2e-7 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 16384, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/codellama-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-8, "output_cost_per_token": 1.2e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "benchmarks": { "local_humaneval_pass1_codellama34b_officiallaunchpost_244": { "label": "HumanEval", "category": "coding", "score": 53.7, "scoreText": "53.7%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 53.7% on HumanEval." }, "local_mbpp_pass1_codellama34b_officiallaunchpost_245": { "label": "MBPP", "category": "coding", "score": 56.2, "scoreText": "56.2%", "metric": "pass@1", "higherIsBetter": true, "source_url": "https://ai.meta.com/blog/code-llama-large-language-model-coding/", "checked_at": "2026-05-31", "baseModelFamily": "CodeLlama", "exactModelOrSnapshot": "Code Llama 34B", "modelDeveloper": "Meta AI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Meta launch post reports the 34B model at 56.2% on MBPP." } } }, { "id": "llamagate/llamagate/qwen3-vl-8b", "slug": "llamagate-llamagate-qwen3-vl-8b", "provider": "llamagate", "providerSlug": "llamagate", "name": "qwen3-vl-8b", "displayName": "qwen3-vl-8b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.55, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5.5e-7 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 32768, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/qwen3-vl-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5.5e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true } }, { "id": "llamagate/llamagate/llava-7b", "slug": "llamagate-llamagate-llava-7b", "provider": "llamagate", "providerSlug": "llamagate", "name": "llava-7b", "displayName": "llava-7b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.19999999999999998, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7 } }, "limits": { "contextWindow": 2048, "maxInputTokens": 4096, "maxOutputTokens": 2048, "maxTokens": 2048, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/llava-7b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 2048, "max_input_tokens": 4096, "max_output_tokens": 2048, "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7, "litellm_provider": "llamagate", "mode": "chat", "supports_response_schema": true, "supports_vision": true } }, { "id": "llamagate/llamagate/gemma3-4b", "slug": "llamagate-llamagate-gemma3-4b", "provider": "llamagate", "providerSlug": "llamagate", "name": "gemma3-4b", "displayName": "gemma3-4b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.03, "outputUsdPer1MTokens": 0.08, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.03, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-8, "output_cost_per_token": 8e-8 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 128000, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "response_schema": true, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/gemma3-4b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 3e-8, "output_cost_per_token": 8e-8, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "benchmarks": { "mmlu_5shot_gemma3pt27b_officialmodelcard_193": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "mmluprocot_5shot_gemma3pt27b_officialmodelcard_194": { "label": "MMLU-Pro (CoT)", "category": "general_knowledge", "score": 52.2, "scoreText": "52.2", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "gpqa_5shot_gemma3pt27b_officialmodelcard_195": { "label": "GPQA", "category": "science", "score": 24.3, "scoreText": "24.3", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "humaneval_0shot_gemma3pt27b_officialmodelcard_196": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "math_4shot_gemma3pt27b_officialmodelcard_197": { "label": "MATH", "category": "math", "score": 50, "scoreText": "50.0", "metric": "4-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official Google Gemma 3 PT model card; used the 27B column from the benchmark table." }, "local_mteb56tasksummary_average_baaibgelargeenv15_officialmodelcard_334": { "label": "MTEB 56-task summary", "category": "other", "score": 64.23, "scoreText": "64.23", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-large-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgebaseenv15_officialmodelcard_335": { "label": "MTEB 56-task summary", "category": "other", "score": 63.55, "scoreText": "63.55", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-base-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_baaibgesmallenv15_officialmodelcard_336": { "label": "MTEB 56-task summary", "category": "other", "score": 62.17, "scoreText": "62.17", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BAAI/bge-small-en-v1.5", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Model-card summary row." }, "local_mteb56tasksummary_average_bgelargeen_officialmodelcard_337": { "label": "MTEB 56-task summary", "category": "other", "score": 63.98, "scoreText": "63.98", "metric": "Average", "higherIsBetter": true, "source_url": "https://huggingface.co/BAAI/bge-large-en-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "bge-large-en", "modelDeveloper": "BAAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Legacy BGE row in the same model-card table." }, "local_mgteretrievaltable_avg_bgem3dense_paper_341": { "label": "mGTE retrieval table", "category": "long_context", "score": 64.3, "scoreText": "64.3", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3sparse_paper_342": { "label": "mGTE retrieval table", "category": "long_context", "score": 55.1, "scoreText": "55.1", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mgteretrievaltable_avg_bgem3densesparse_paper_343": { "label": "mGTE retrieval table", "category": "long_context", "score": 67.7, "scoreText": "67.7", "metric": "Avg", "higherIsBetter": true, "source_url": "https://huggingface.co/Alibaba-NLP/gte-multilingual-base/resolve/087a024525fd6e2fe749cb4679d218d8bcc95bdd/images/mgte-retrieval.pdf?download=true", "checked_at": "2026-05-31", "baseModelFamily": "bge", "exactModelOrSnapshot": "BGE-M3 Dense + Sparse", "modelDeveloper": "BAAI", "sourceType": "paper", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Rows copied from the published retrieval table used by the GTE model card." }, "local_mmlu_5shot_gemma3pt27b_officialmodelcard_29": { "label": "MMLU", "category": "general_knowledge", "score": 78.6, "scoreText": "78.6", "metric": "5-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_gsm8k_8shot_gemma3pt27b_officialmodelcard_30": { "label": "GSM8K", "category": "math", "score": 82.6, "scoreText": "82.6", "metric": "8-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_humaneval_0shot_gemma3pt27b_officialmodelcard_31": { "label": "HumanEval", "category": "coding", "score": 48.8, "scoreText": "48.8", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 STEM and code table on the 4B/12B/27B model card; 27B column." }, "local_mgsm_0shot_gemma3pt27b_officialmodelcard_32": { "label": "MGSM", "category": "math", "score": 74.3, "scoreText": "74.3", "metric": "0-shot", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multilingual table on the 4B/12B/27B model card; 27B column." }, "local_docvqa_val_gemma3pt27b_officialmodelcard_33": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "val", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_mmmu_pt_gemma3pt27b_officialmodelcard_34": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "pt", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-4b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the Gemma 3 multimodal table on the 4B/12B/27B model card; 27B column." }, "local_docvqaval_score_gemma3pt27b_officialmodelcard_382": { "label": "DocVQA", "category": "multimodal", "score": 85.6, "scoreText": "85.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_infovqaval_score_gemma3pt27b_officialmodelcard_383": { "label": "InfoVQA", "category": "multimodal", "score": 59.4, "scoreText": "59.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_mmmupt_score_gemma3pt27b_officialmodelcard_384": { "label": "MMMU", "category": "multimodal", "score": 56.1, "scoreText": "56.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_textvqaval_score_gemma3pt27b_officialmodelcard_385": { "label": "TextVQA", "category": "multimodal", "score": 68.6, "scoreText": "68.6", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_ai2d_score_gemma3pt27b_officialmodelcard_386": { "label": "AI2D", "category": "multimodal", "score": 79, "scoreText": "79.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." }, "local_chartqa_score_gemma3pt27b_officialmodelcard_387": { "label": "ChartQA", "category": "multimodal", "score": 76.3, "scoreText": "76.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/google/gemma-3-27b-pt", "checked_at": "2026-05-31", "baseModelFamily": "Gemma 3", "exactModelOrSnapshot": "Gemma 3 PT 27B", "modelDeveloper": "Google DeepMind", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official multimodal results table from the Gemma 3 card." } } }, { "id": "llamagate/llamagate/nomic-embed-text", "slug": "llamagate-llamagate-nomic-embed-text", "provider": "llamagate", "providerSlug": "llamagate", "name": "nomic-embed-text", "displayName": "nomic-embed-text", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 8192, "maxOutputTokens": null, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/nomic-embed-text", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "litellm_provider": "llamagate", "mode": "embedding" }, "benchmarks": { "local_performancebenchmarks_mteb_nomicembedtextv1_officialmodelcard_319": { "label": "Performance Benchmarks", "category": "other", "score": 62.39, "scoreText": "62.39", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported model-card benchmark table." }, "local_performancebenchmarks_loco_nomicembedtextv1_officialmodelcard_320": { "label": "Performance Benchmarks", "category": "long_context", "score": 85.53, "scoreText": "85.53", "metric": "LoCo", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported model-card benchmark table." }, "local_performancebenchmarks_jinalongcontext_nomicembedtextv1_officialmodelcard_321": { "label": "Performance Benchmarks", "category": "long_context", "score": 54.16, "scoreText": "54.16", "metric": "Jina Long Context", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Self-reported model-card benchmark table." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_322": { "label": "Adjusting Dimensionality", "category": "other", "score": 62.28, "scoreText": "62.28", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 768 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_323": { "label": "Adjusting Dimensionality", "category": "other", "score": 61.96, "scoreText": "61.96", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 512 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_324": { "label": "Adjusting Dimensionality", "category": "other", "score": 61.04, "scoreText": "61.04", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 256 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_325": { "label": "Adjusting Dimensionality", "category": "other", "score": 59.34, "scoreText": "59.34", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 128 row from the model card." }, "local_adjustingdimensionality_mteb_nomicembedtextv15_officialmodelcard_326": { "label": "Adjusting Dimensionality", "category": "other", "score": 56.1, "scoreText": "56.10", "metric": "MTEB", "higherIsBetter": true, "source_url": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5", "checked_at": "2026-05-31", "baseModelFamily": "nomic-embed", "exactModelOrSnapshot": "nomic-embed-text-v1.5", "modelDeveloper": "Nomic AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Dimension 64 row from the model card." } } }, { "id": "llamagate/llamagate/qwen3-embedding-8b", "slug": "llamagate-llamagate-qwen3-embedding-8b", "provider": "llamagate", "providerSlug": "llamagate", "name": "qwen3-embedding-8b", "displayName": "qwen3-embedding-8b", "mode": "embedding", "pricing": { "inputUsdPer1MTokens": 0.02, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.02, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 2e-8, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 40960, "maxInputTokens": 40960, "maxOutputTokens": null, "maxTokens": 40960, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "llamagate/qwen3-embedding-8b", "syncedAt": "2026-05-28" }, "rawLitellm": { "max_tokens": 40960, "max_input_tokens": 40960, "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "litellm_provider": "llamagate", "mode": "embedding" }, "benchmarks": { "local_qwen3evaluationsuite_mtebr_qwen3embedding06b_officialmodelcard_352": { "label": "Qwen3 evaluation suite", "category": "other", "score": 61.82, "scoreText": "61.82", "metric": "MTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_cmtebr_qwen3embedding06b_officialmodelcard_353": { "label": "Qwen3 evaluation suite", "category": "other", "score": 71.02, "scoreText": "71.02", "metric": "CMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mmtebr_qwen3embedding06b_officialmodelcard_354": { "label": "Qwen3 evaluation suite", "category": "other", "score": 64.64, "scoreText": "64.64", "metric": "MMTEB-R", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mldr_qwen3embedding06b_officialmodelcard_355": { "label": "Qwen3 evaluation suite", "category": "other", "score": 50.26, "scoreText": "50.26", "metric": "MLDR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_mtebcode_qwen3embedding06b_officialmodelcard_356": { "label": "Qwen3 evaluation suite", "category": "other", "score": 75.41, "scoreText": "75.41", "metric": "MTEB-Code", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." }, "local_qwen3evaluationsuite_followir_qwen3embedding06b_officialmodelcard_357": { "label": "Qwen3 evaluation suite", "category": "other", "score": 5.09, "scoreText": "5.09", "metric": "FollowIR", "higherIsBetter": true, "source_url": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B", "checked_at": "2026-05-31", "baseModelFamily": "qwen3-embedding", "exactModelOrSnapshot": "Qwen3-Embedding-0.6B", "modelDeveloper": "Qwen", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Published evaluation table row for the 0.6B embedding model." } } }, { "id": "sarvam/sarvam/sarvam-m", "slug": "sarvam-sarvam-sarvam-m", "provider": "sarvam", "providerSlug": "sarvam", "name": "sarvam-m", "displayName": "sarvam-m", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "zero_raw_unclassified", "cacheWritePriceStatus": "zero_raw_unclassified", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0, "cache_creation_input_token_cost_above_1hr": 0, "cache_read_input_token_cost": 0, "input_cost_per_token": 0, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32000, "maxInputTokens": 8192, "maxOutputTokens": 32000, "maxTokens": 32000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "reasoning": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sarvam/sarvam-m", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0, "cache_creation_input_token_cost_above_1hr": 0, "cache_read_input_token_cost": 0, "input_cost_per_token": 0, "litellm_provider": "sarvam", "max_input_tokens": 8192, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0, "supports_reasoning": true } }, { "id": "openai/tts-1-1106", "slug": "openai-tts-1-1106", "provider": "OpenAI", "providerSlug": "openai", "name": "tts-1-1106", "displayName": "tts-1-1106", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.000015, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.000015 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "tts-1-1106", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.000015, "litellm_provider": "openai", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "openai/tts-1-hd-1106", "slug": "openai-tts-1-hd-1106", "provider": "OpenAI", "providerSlug": "openai", "name": "tts-1-hd-1106", "displayName": "tts-1-hd-1106", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": 0.00003, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_character": 0.00003 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "tts-1-hd-1106", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_character": 0.00003, "litellm_provider": "openai", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] } }, { "id": "openai/gpt-4o-mini-tts-2025-03-20", "slug": "openai-gpt-4o-mini-tts-2025-03-20", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-tts-2025-03-20", "displayName": "gpt-4o-mini-tts-2025-03-20", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": 12, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.00025, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "audio" ] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-tts-2025-03-20", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "mode": "audio_speech", "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ] }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-tts-2025-12-15", "slug": "openai-gpt-4o-mini-tts-2025-12-15", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-tts-2025-12-15", "displayName": "gpt-4o-mini-tts-2025-12-15", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": 2.5, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": 12, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 2.5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": 0.00025, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.0000025, "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "audio" ] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-tts-2025-12-15", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "mode": "audio_speech", "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ] }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-transcribe-2025-03-20", "slug": "openai-gpt-4o-mini-transcribe-2025-03-20", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-transcribe-2025-03-20", "displayName": "gpt-4o-mini-transcribe-2025-03-20", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1.25, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": null, "maxInputTokens": 16000, "maxOutputTokens": 2000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-transcribe-2025-03-20", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 0.000005, "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-4o-mini-transcribe-2025-12-15", "slug": "openai-gpt-4o-mini-transcribe-2025-12-15", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-4o-mini-transcribe-2025-12-15", "displayName": "gpt-4o-mini-transcribe-2025-12-15", "mode": "audio_transcription", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1.25, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.000005 } }, "limits": { "contextWindow": null, "maxInputTokens": 16000, "maxOutputTokens": 2000, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "audio" ], "output": [ "text" ] }, "endpoints": [ "/v1/audio/transcriptions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-4o-mini-transcribe-2025-12-15", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_audio_token": 0.00000125, "input_cost_per_token": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 0.000005, "supported_endpoints": [ "/v1/audio/transcriptions" ], "manual_modalities_contract_id": "audio_transcription", "manual_modalities_review_status": "reviewed_endpoint_contract" }, "benchmarks": { "swebenchverified_accuracy_gpt4o20241120_officiallaunchpost_7": { "label": "SWE-bench Verified", "category": "coding", "score": 33.2, "scoreText": "33.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Snapshot value from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_8": { "label": "Aider Polyglot", "category": "coding", "score": 30.7, "scoreText": "30.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Whole-format coding score from the GPT-4.1 appendix comparison table." }, "aiderpolyglot_accuracy_gpt4o20241120_officiallaunchpost_9": { "label": "Aider Polyglot", "category": "coding", "score": 18.2, "scoreText": "18.2%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Diff-format coding score from the GPT-4.1 appendix comparison table." }, "ifeval_accuracy_gpt4o20241120_officiallaunchpost_10": { "label": "IFEval", "category": "agentic", "score": 81, "scoreText": "81.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o", "exactModelOrSnapshot": "GPT-4o (2024-11-20)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Instruction-following snapshot score in the GPT-4.1 appendix comparison table." }, "designarena3d_elo_openaigpt4o_benchmarkleaderboard_263": { "label": "Design Arena - 3D", "category": "preference", "score": 958, "scoreText": "958 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenacodecategories_elo_openaigpt4o_benchmarkleaderboard_264": { "label": "Design Arena - Code Categories", "category": "preference", "score": 918, "scoreText": "918 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenagamedevelopment_elo_openaigpt4o_benchmarkleaderboard_265": { "label": "Design Arena - Game Development", "category": "preference", "score": 983, "scoreText": "983 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "designarenawebsite_elo_openaigpt4o_benchmarkleaderboard_266": { "label": "Design Arena - Website", "category": "preference", "score": 882, "scoreText": "882 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-4o/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o", "exactModelOrSnapshot": "openai/gpt-4o", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Design Arena score; keep as candidate only." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_11": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/gpt-4-1/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-4o-mini", "exactModelOrSnapshot": "GPT-4o mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Appendix comparison table in the GPT-4.1 launch post." }, "mmlu_accuracy_gpt4omini_officiallaunchpost_261": { "label": "MMLU", "category": "general_knowledge", "score": 82, "scoreText": "82%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openai.com/et-EE/index/gpt-4o-mini-advancing-cost-efficient-intelligence/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-4o mini", "exactModelOrSnapshot": "gpt-4o-mini", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Exact MMLU score is explicitly stated." } } }, { "id": "openai/gpt-5-search-api", "slug": "openai-gpt-5-search-api", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-search-api", "displayName": "gpt-5-search-api", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": true, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false, "minimal_reasoning_effort": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-search-api", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openai/gpt-5-search-api-2025-10-14", "slug": "openai-gpt-5-search-api-2025-10-14", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-5-search-api-2025-10-14", "displayName": "gpt-5-search-api-2025-10-14", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 272000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true, "none_reasoning_effort": false, "xhigh_reasoning_effort": false } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-5-search-api-2025-10-14", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false }, "benchmarks": { "swebenchverified_accuracy_gpt5high_officiallaunchpost_21": { "label": "SWE-bench Verified", "category": "coding", "score": 74.9, "scoreText": "74.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort." }, "aiderpolyglot_accuracy_gpt5high_officiallaunchpost_22": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; code-editing benchmark, high reasoning effort." }, "gpqadiamond_accuracy_gpt5high_officiallaunchpost_23": { "label": "GPQA Diamond", "category": "general_knowledge", "score": 85.7, "scoreText": "85.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; no tools." }, "aime2025_accuracy_gpt5high_officiallaunchpost_24": { "label": "AIME 2025", "category": "reasoning", "score": 94.6, "scoreText": "94.6%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Comparison table in the GPT-5 developer post; high reasoning effort, no tools." }, "tau2benchtelecom_accuracy_gpt5high_officiallaunchpost_25": { "label": "Tau2-bench Telecom", "category": "agentic", "score": 96.7, "scoreText": "96.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://openai.com/index/introducing-gpt-5-for-developers/", "checked_at": "2026-05-31", "baseModelFamily": "gpt-5", "exactModelOrSnapshot": "GPT-5 (high)", "modelDeveloper": "OpenAI", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Tool-calling benchmark callout in the GPT-5 developer post." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_220": { "label": "Aider Polyglot", "category": "coding", "score": 88, "scoreText": "88.0%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the high reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_221": { "label": "Aider Polyglot", "category": "coding", "score": 86.7, "scoreText": "86.7%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the medium reasoning-effort run." }, "aiderpolyglot_percentcorrect_openaigpt5_benchmarkleaderboard_222": { "label": "Aider Polyglot", "category": "coding", "score": 81.3, "scoreText": "81.3%", "metric": "percent correct", "higherIsBetter": true, "source_url": "https://aider.chat/docs/leaderboards/", "checked_at": "2026-05-31", "baseModelFamily": "GPT-5", "exactModelOrSnapshot": "openai/gpt-5", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Aider polyglot leaderboard row for the low reasoning-effort run." } } }, { "id": "openai/gpt-realtime-mini-2025-10-06", "slug": "openai-gpt-realtime-mini-2025-10-06", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-realtime-mini-2025-10-06", "displayName": "gpt-realtime-mini-2025-10-06", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": 0.06, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": 0.7999999999999999, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 6e-8, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-realtime-mini-2025-10-06", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 6e-8, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "input_cost_per_token": 6e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/gpt-realtime-mini-2025-12-15", "slug": "openai-gpt-realtime-mini-2025-12-15", "provider": "OpenAI", "providerSlug": "openai", "name": "gpt-realtime-mini-2025-12-15", "displayName": "gpt-realtime-mini-2025-12-15", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.6, "outputUsdPer1MTokens": 2.4, "cachedInputUsdPer1MTokens": 0.06, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 10, "audioOutputUsdPer1MTokens": 20, "imageInputUsdPer1MUnits": 0.7999999999999999, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.6, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 6e-8, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "input_cost_per_token": 6e-7, "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024 } }, "limits": { "contextWindow": 4096, "maxInputTokens": 128000, "maxOutputTokens": 4096, "maxTokens": 4096, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": true, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "parallel_function_calling": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text", "image", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gpt-realtime-mini-2025-12-15", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "cache_read_input_token_cost": 6e-8, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "input_cost_per_token": 6e-7, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.0000024, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true } }, { "id": "openai/sora-2", "slug": "openai-sora-2", "provider": "OpenAI", "providerSlug": "openai", "name": "sora-2", "displayName": "sora-2", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.1 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sora-2", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.openai.com/docs/api-reference/videos" }, "rawLitellm": { "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "720x1280", "1280x720" ] } }, { "id": "openai/sora-2-pro", "slug": "openai-sora-2-pro", "provider": "OpenAI", "providerSlug": "openai", "name": "sora-2-pro", "displayName": "sora-2-pro", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.3 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sora-2-pro", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.openai.com/docs/api-reference/videos" }, "rawLitellm": { "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "720x1280", "1280x720" ] } }, { "id": "openai/sora-2-pro-high-res", "slug": "openai-sora-2-pro-high-res", "provider": "OpenAI", "providerSlug": "openai", "name": "sora-2-pro-high-res", "displayName": "sora-2-pro-high-res", "mode": "video_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "output_cost_per_video_per_second": 0.5 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "video" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "sora-2-pro-high-res", "syncedAt": "2026-05-28", "sourceUrl": "https://platform.openai.com/docs/api-reference/videos" }, "rawLitellm": { "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_resolutions": [ "1024x1792", "1792x1024" ] } }, { "id": "openai/chatgpt-image-latest", "slug": "openai-chatgpt-image-latest", "provider": "OpenAI", "providerSlug": "openai", "name": "chatgpt-image-latest", "displayName": "chatgpt-image-latest", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": 5, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": 1.25, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 5, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_image_token_cost": 0.0000025, "cache_read_input_token_cost": 0.00000125, "input_cost_per_image_token": 0.00001, "input_cost_per_token": 0.000005, "output_cost_per_image_token": 0.00004 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "chatgpt-image-latest", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_read_input_image_token_cost": 0.0000025, "cache_read_input_token_cost": 0.00000125, "input_cost_per_image_token": 0.00001, "input_cost_per_token": 0.000005, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 0.00004, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] } }, { "id": "gemini/gemini-2.0-flash-exp-image-generation", "slug": "gemini-gemini-2-0-flash-exp-image-generation", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.0-flash-exp-image-generation", "displayName": "gemini-2.0-flash-exp-image-generation", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 39000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_image": 0.039, "output_cost_per_token": 0 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.0-flash-exp-image-generation", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "gemini", "max_images_per_prompt": 3000, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_token": 0, "source": "https://ai.google.dev/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_vision": true }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." } } }, { "id": "gemini/gemini/gemini-2.0-flash-exp-image-generation", "slug": "gemini-gemini-gemini-2-0-flash-exp-image-generation", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.0-flash-exp-image-generation", "displayName": "gemini-2.0-flash-exp-image-generation", "mode": "image_generation", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": 39000, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0, "output_cost_per_image": 0.039, "output_cost_per_token": 0, "tpm": 250000, "rpm": 10 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 32768, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 10, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "vision": true } }, "modalities": { "supported": [ "text", "image" ], "input": [], "output": [ "text", "image" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.0-flash-exp-image-generation", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_token": 0, "litellm_provider": "gemini", "max_images_per_prompt": 3000, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_token": 0, "source": "https://ai.google.dev/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_vision": true, "tpm": 250000, "rpm": 10 }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." } } }, { "id": "gemini/gemini/gemini-2.0-flash-lite-001", "slug": "gemini-gemini-gemini-2-0-flash-lite-001", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.0-flash-lite-001", "displayName": "gemini-2.0-flash-lite-001", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": 0.01875, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 0.075, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.875e-8, "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "rpm": 4000, "tpm": 4000000 } }, "limits": { "contextWindow": null, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": null, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 50, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 4000, "tpm": 4000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": false, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": true, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": true, "function_calling": true, "prompt_caching": true, "response_schema": true, "system_messages": true, "tool_choice": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": "2026-06-01", "status": "deprecated", "announcementDate": null, "shutdownDate": "2026-06-01", "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.0-flash-lite-001", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite" }, "rawLitellm": { "cache_read_input_token_cost": 1.875e-8, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_pdf_size_mb": 50, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 3e-7, "rpm": 4000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "tpm": 4000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash-lite" ], "manual_model_modalities_note": "Google Gemini exact alias override from version list", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": null }, "benchmarks": { "mmlupro_accuracy_gemini20flashga_officialmodelcard_74": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 77.6, "scoreText": "77.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashga_officialmodelcard_75": { "label": "LiveCodeBench v5", "category": "coding", "score": 34.5, "scoreText": "34.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashga_officialmodelcard_76": { "label": "GPQA Diamond", "category": "science", "score": 60.1, "scoreText": "60.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "math_accuracy_gemini20flashga_officialmodelcard_77": { "label": "MATH", "category": "math", "score": 90.9, "scoreText": "90.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashga_officialmodelcard_78": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 84.6, "scoreText": "84.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash", "exactModelOrSnapshot": "Gemini 2.0 Flash (GA)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "GA column from the cross-family comparison table." }, "mmlupro_accuracy_gemini20flashlitepublicpreview_officialmodelcard_79": { "label": "MMLU-Pro", "category": "general_knowledge", "score": 71.6, "scoreText": "71.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "livecodebenchv5_accuracy_gemini20flashlitepublicpreview_officialmodelcard_80": { "label": "LiveCodeBench v5", "category": "coding", "score": 28.9, "scoreText": "28.9%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "gpqadiamond_accuracy_gemini20flashlitepublicpreview_officialmodelcard_81": { "label": "GPQA Diamond", "category": "science", "score": 51.5, "scoreText": "51.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "math_accuracy_gemini20flashlitepublicpreview_officialmodelcard_82": { "label": "MATH", "category": "math", "score": 86.8, "scoreText": "86.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." }, "factsgrounding_accuracy_gemini20flashlitepublicpreview_officialmodelcard_83": { "label": "FACTS Grounding", "category": "general_knowledge", "score": 83.6, "scoreText": "83.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-0-Flash-Lite-Model-Card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "Gemini 2.0 Flash-Lite", "exactModelOrSnapshot": "Gemini 2.0 Flash-Lite (Public Preview)", "modelDeveloper": "Google", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Public Preview column from the cross-family comparison table." } } }, { "id": "gemini/gemini-2.5-flash-native-audio-latest", "slug": "gemini-gemini-2-5-flash-native-audio-latest", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-native-audio-latest", "displayName": "gemini-2.5-flash-native-audio-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-flash-native-audio-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true } }, { "id": "gemini/gemini-2.5-flash-native-audio-preview-09-2025", "slug": "gemini-gemini-2-5-flash-native-audio-preview-09-2025", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-native-audio-preview-09-2025", "displayName": "gemini-2.5-flash-native-audio-preview-09-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true } }, "modalities": { "supported": [ "audio", "text", "video" ], "input": [ "audio", "text", "video" ], "output": [ "audio", "text" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-flash-native-audio-preview-09-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/gemini" ], "manual_model_modalities_note": "Google Gemini 2.5 Flash Live version-list override from model page" } }, { "id": "gemini/gemini-2.5-flash-native-audio-preview-12-2025", "slug": "gemini-gemini-2-5-flash-native-audio-preview-12-2025", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-native-audio-preview-12-2025", "displayName": "gemini-2.5-flash-native-audio-preview-12-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true } }, "modalities": { "supported": [ "audio", "text", "video" ], "input": [ "audio", "text", "video" ], "output": [ "audio", "text" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-flash-native-audio-preview-12-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-native-audio-preview-12-2025", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Audio, video, text Output Audio and text" } }, { "id": "gemini/gemini-3.1-flash-live-preview", "slug": "gemini-gemini-3-1-flash-live-preview", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3.1-flash-live-preview", "displayName": "gemini-3.1-flash-live-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.75, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 3, "audioOutputUsdPer1MTokens": 12, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000003, "input_cost_per_image_token": 0.000001, "input_cost_per_token": 7.5e-7, "input_cost_per_video_per_second": 0.000033333333333333335, "output_cost_per_audio_token": 0.000012, "output_cost_per_token": 0.0000045 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 131072, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": true, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-3.1-flash-live-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "input_cost_per_audio_token": 0.000003, "input_cost_per_image_token": 0.000001, "input_cost_per_token": 7.5e-7, "input_cost_per_video_per_second": 0.000033333333333333335, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_audio_token": 0.000012, "output_cost_per_token": 0.0000045, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-live-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, images, audio, video Output Text and audio" } }, { "id": "gemini/gemini/gemini-2.5-flash-native-audio-latest", "slug": "gemini-gemini-gemini-2-5-flash-native-audio-latest", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-native-audio-latest", "displayName": "gemini-2.5-flash-native-audio-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "tpm": 250000, "rpm": 10 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 10, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true } }, "modalities": { "supported": [ "text", "audio" ], "input": [], "output": [ "text", "audio" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-flash-native-audio-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, "rpm": 10 } }, { "id": "gemini/gemini/gemini-2.5-flash-native-audio-preview-09-2025", "slug": "gemini-gemini-gemini-2-5-flash-native-audio-preview-09-2025", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-native-audio-preview-09-2025", "displayName": "gemini-2.5-flash-native-audio-preview-09-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "tpm": 250000, "rpm": 10 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 10, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true } }, "modalities": { "supported": [ "audio", "text", "video" ], "input": [ "audio", "text", "video" ], "output": [ "audio", "text" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-flash-native-audio-preview-09-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, "rpm": 10, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://ai.google.dev/gemini-api/docs/models/gemini" ], "manual_model_modalities_note": "Google Gemini 2.5 Flash Live version-list override from model page" } }, { "id": "gemini/gemini/gemini-2.5-flash-native-audio-preview-12-2025", "slug": "gemini-gemini-gemini-2-5-flash-native-audio-preview-12-2025", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-native-audio-preview-12-2025", "displayName": "gemini-2.5-flash-native-audio-preview-12-2025", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "tpm": 250000, "rpm": 10 } }, "limits": { "contextWindow": 8192, "maxInputTokens": 1048576, "maxOutputTokens": 8192, "maxTokens": 8192, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 10, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": true, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true } }, "modalities": { "supported": [ "audio", "text", "video" ], "input": [ "audio", "text", "video" ], "output": [ "audio", "text" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null, "status": null, "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-2.5-flash-native-audio-preview-12-2025", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, "rpm": 10, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-native-audio-preview-12-2025", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Audio, video, text Output Audio and text", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." } }, { "id": "gemini/gemini/gemini-3.1-flash-live-preview", "slug": "gemini-gemini-gemini-3-1-flash-live-preview", "provider": "Google", "providerSlug": "gemini", "name": "gemini-3.1-flash-live-preview", "displayName": "gemini-3.1-flash-live-preview", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.75, "outputUsdPer1MTokens": 4.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": 3, "audioOutputUsdPer1MTokens": 12, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.75, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_audio_token": 0.000003, "input_cost_per_image_token": 0.000001, "input_cost_per_token": 7.5e-7, "input_cost_per_video_per_second": 0.000033333333333333335, "output_cost_per_audio_token": 0.000012, "output_cost_per_token": 0.0000045, "tpm": 250000, "rpm": 10 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 131072, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": 10, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": true, "audioOutput": true, "webSearch": true, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "audio_output": true, "function_calling": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "audio", "image", "text", "video" ], "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "endpoints": [ "/v1/realtime" ], "lifecycle": { "deprecationDate": null, "status": null, "announcementDate": null, "shutdownDate": null, "earliestShutdownDate": null, "sourceUrls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "checkedAt": "2026-05-30", "reviewStatus": "reviewed_official_docs_exact_model", "note": "Google lists 'No shutdown date announced'." }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-3.1-flash-live-preview", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "rawLitellm": { "input_cost_per_audio_token": 0.000003, "input_cost_per_image_token": 0.000001, "input_cost_per_token": 7.5e-7, "input_cost_per_video_per_second": 0.000033333333333333335, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_audio_token": 0.000012, "output_cost_per_token": 0.0000045, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "rpm": 10, "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-live-preview", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text, images, audio, video Output Text and audio", "manual_model_lifecycle_review_status": "reviewed_official_docs_exact_model", "manual_model_lifecycle_source_urls": [ "https://ai.google.dev/gemini-api/docs/deprecations" ], "manual_model_lifecycle_checked_at": "2026-05-30", "manual_model_lifecycle_note": "Google lists 'No shutdown date announced'." } }, { "id": "gemini/gemini-2.5-flash-preview-tts", "slug": "gemini-gemini-2-5-flash-preview-tts", "provider": "Google", "providerSlug": "gemini", "name": "gemini-2.5-flash-preview-tts", "displayName": "gemini-2.5-flash-preview-tts", "mode": "audio_speech", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "audio", "text" ], "input": [ "text" ], "output": [ "audio" ] }, "endpoints": [ "/v1/audio/speech" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-2.5-flash-preview-tts", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/pricing" }, "rawLitellm": { "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "mode": "audio_speech", "output_cost_per_token": 0.0000025, "source": "https://ai.google.dev/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "google_gemini_modalities_source_url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-preview-tts", "google_gemini_modalities_fetched_at": "2026-05-28T01:25:36.714Z", "google_gemini_supported_data_types": "Inputs Text Output Audio" } }, { "id": "gemini/gemini-flash-latest", "slug": "gemini-gemini-flash-latest", "provider": "Google", "providerSlug": "gemini", "name": "gemini-flash-latest", "displayName": "gemini-flash-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "tpm": 8000000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 100000, "tpm": 8000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-flash-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview" }, "rawLitellm": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } } }, { "id": "gemini/gemini-flash-lite-latest", "slug": "gemini-gemini-flash-lite-latest", "provider": "Google", "providerSlug": "gemini", "name": "gemini-flash-lite-latest", "displayName": "gemini-flash-lite-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.09999999999999999, "outputUsdPer1MTokens": 0.39999999999999997, "cachedInputUsdPer1MTokens": 0.01, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 0.39999999999999997, "audioInputUsdPer1MTokens": 0.3, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.09999999999999999, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, "tpm": 250000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 15, "tpm": 250000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-flash-lite-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite" }, "rawLitellm": { "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } } }, { "id": "gemini/gemini-pro-latest", "slug": "gemini-gemini-pro-latest", "provider": "Google", "providerSlug": "gemini", "name": "gemini-pro-latest", "displayName": "gemini-pro-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 2.5, "above200kOutputUsdPer1MTokens": 15, "above200kCachedInputUsdPer1MTokens": 0.25, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "tpm": 800000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-pro-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } } }, { "id": "gemini/gemini/gemini-pro-latest", "slug": "gemini-gemini-gemini-pro-latest", "provider": "Google", "providerSlug": "gemini", "name": "gemini-pro-latest", "displayName": "gemini-pro-latest", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.25, "outputUsdPer1MTokens": 10, "cachedInputUsdPer1MTokens": 0.125, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.25, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": 2.5, "above200kOutputUsdPer1MTokens": 15, "above200kCachedInputUsdPer1MTokens": 0.25, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "tpm": 800000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 2000, "tpm": 800000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": true, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": true, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_input": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "video_input": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini/gemini-pro-latest", "syncedAt": "2026-05-28", "sourceUrl": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "rawLitellm": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } } }, { "id": "gemini/gemini-exp-1206", "slug": "gemini-gemini-exp-1206", "provider": "Google", "providerSlug": "gemini", "name": "gemini-exp-1206", "displayName": "gemini-exp-1206", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.3, "outputUsdPer1MTokens": 2.5, "cachedInputUsdPer1MTokens": 0.03, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": 2.5, "audioInputUsdPer1MTokens": 1, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "tpm": 8000000 } }, "limits": { "contextWindow": 65535, "maxInputTokens": 1048576, "maxOutputTokens": 65535, "maxTokens": 65535, "maxImagesPerPrompt": 3000, "maxAudioPerPrompt": 1, "maxAudioLengthHours": 8.4, "maxPdfSizeMb": 30, "maxVideoLength": 1, "maxVideosPerPrompt": 10, "outputVectorSize": null, "rpm": 100000, "tpm": 8000000, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": true, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": true, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "audio_output": false, "function_calling": true, "parallel_function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "system_messages": true, "tool_choice": true, "url_context": true, "vision": true, "web_search": true } }, "modalities": { "supported": [ "text", "image", "audio", "video" ], "input": [], "output": [ "text" ] }, "endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "gemini-exp-1206", "syncedAt": "2026-05-28", "sourceUrl": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview" }, "rawLitellm": { "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "mode": "chat", "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } } }, { "id": "vertex_ai-anthropic_models/vertex_ai/claude-sonnet-4-6@default", "slug": "vertex_ai-anthropic_models-vertex_ai-claude-sonnet-4-6-default", "provider": "vertex_ai-anthropic_models", "providerSlug": "vertex_ai-anthropic_models", "name": "claude-sonnet-4-6@default", "displayName": "claude-sonnet-4-6@default", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 3, "outputUsdPer1MTokens": 15, "cachedInputUsdPer1MTokens": 0.3, "cacheWriteUsdPer1MTokens": 3.75, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 3, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 1000000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": true, "reasoningEfforts": { "none": false, "minimal": true, "max": true, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "pdf_input": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "max_reasoning_effort": true, "tool_choice": true, "vision": true, "output_config": true, "minimal_reasoning_effort": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "vertex_ai/claude-sonnet-4-6@default", "syncedAt": "2026-05-28" }, "rawLitellm": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000015, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_output_config": true, "supports_minimal_reasoning_effort": true }, "benchmarks": { "swebenchverified_score_claudesonnet4_officiallaunchpost_53": { "label": "SWE-bench Verified", "category": "coding", "score": 72.7, "scoreText": "72.7%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; no extended thinking." }, "gpqadiamond_score_claudesonnet4_officiallaunchpost_56": { "label": "GPQA Diamond", "category": "science", "score": 70, "scoreText": "70.0%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmlu_score_claudesonnet4_officiallaunchpost_58": { "label": "MMMLU", "category": "general_knowledge", "score": 85.4, "scoreText": "85.4%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "mmmu_score_claudesonnet4_officiallaunchpost_60": { "label": "MMMU", "category": "multimodal", "score": 72.6, "scoreText": "72.6%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-4", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4", "exactModelOrSnapshot": "Claude Sonnet 4", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post; w/o extended thinking." }, "livebench_livebenchscore_claude46sonnetthinkingmediumeffort_benchmarkleaderboard_233": { "label": "LiveBench", "category": "general_knowledge", "score": 75.47, "scoreText": "75.47", "metric": "LiveBench score", "higherIsBetter": true, "source_url": "https://livebench.ai/", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.6 Sonnet", "exactModelOrSnapshot": "Claude 4.6 Sonnet Thinking Medium Effort", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official LiveBench homepage leaderboard snapshot; route-specific thinking variant." }, "artificialanalysisintelligenceindex_indexscore_anthropicclaudesonnet46_benchmarkleaderboard_267": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 51.7, "scoreText": "51.7", "metric": "index score", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "gpqadiamond_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_268": { "label": "GPQA Diamond", "category": "reasoning", "score": 87.5, "scoreText": "87.5%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudesonnet46_benchmarkleaderboard_269": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 53, "scoreText": "53.0%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "hle_accuracy_anthropicclaudesonnet46_benchmarkleaderboard_270": { "label": "Humanity's Last Exam", "category": "general_knowledge", "score": 30, "scoreText": "30.0%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Sonnet 4.6", "exactModelOrSnapshot": "anthropic/claude-sonnet-4.6", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "duckduckgo/duckduckgo/search", "slug": "duckduckgo-duckduckgo-search", "provider": "duckduckgo", "providerSlug": "duckduckgo", "name": "search", "displayName": "search", "mode": "search", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_query": 0 } }, "limits": { "contextWindow": null, "maxInputTokens": null, "maxOutputTokens": null, "maxTokens": null, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": false, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": false, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": {} }, "modalities": { "supported": [ "query", "search_results" ], "input": [ "query" ], "output": [ "search_results" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "duckduckgo/search", "syncedAt": "2026-05-28" }, "rawLitellm": { "litellm_provider": "duckduckgo", "mode": "search", "input_cost_per_query": 0, "metadata": { "notes": "DuckDuckGo Instant Answer API is free and does not require an API key." }, "manual_modalities_contract_id": "search_query_results", "manual_modalities_review_status": "reviewed_endpoint_contract" } }, { "id": "bedrock_mantle/bedrock_mantle/openai.gpt-oss-120b", "slug": "bedrock_mantle-bedrock_mantle-openai-gpt-oss-120b", "provider": "bedrock_mantle", "providerSlug": "bedrock_mantle", "name": "openai.gpt-oss-120b", "displayName": "openai.gpt-oss-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock_mantle/openai.gpt-oss-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "aime2025_accuracy_gptoss120b_officialmodelcard_35": { "label": "AIME 2025", "category": "reasoning", "score": 97.9, "scoreText": "97.9%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "swebenchverified_accuracy_gptoss120b_officialmodelcard_36": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss120b_officialmodelcard_37": { "label": "Codeforces", "category": "coding", "score": 2622, "scoreText": "2622 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-120b", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "bedrock_mantle/bedrock_mantle/openai.gpt-oss-20b", "slug": "bedrock_mantle-bedrock_mantle-openai-gpt-oss-20b", "provider": "bedrock_mantle", "providerSlug": "bedrock_mantle", "name": "openai.gpt-oss-20b", "displayName": "openai.gpt-oss-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 32768, "maxInputTokens": 131072, "maxOutputTokens": 32768, "maxTokens": 32768, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": true, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "parallel_function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock_mantle/openai.gpt-oss-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "swebenchverified_accuracy_gptoss20b_officialmodelcard_38": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning." }, "codeforces_elo_gptoss20b_officialmodelcard_39": { "label": "Codeforces", "category": "coding", "score": 2516, "scoreText": "2516 Elo", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss-20b", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3; high reasoning with tools." }, "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "bedrock_mantle/bedrock_mantle/openai.gpt-oss-safeguard-120b", "slug": "bedrock_mantle-bedrock_mantle-openai-gpt-oss-safeguard-120b", "provider": "bedrock_mantle", "providerSlug": "bedrock_mantle", "name": "openai.gpt-oss-safeguard-120b", "displayName": "openai.gpt-oss-safeguard-120b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.15, "outputUsdPer1MTokens": 0.6, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.15, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 131072, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock_mantle/openai.gpt-oss-safeguard-120b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "bedrock_mantle/bedrock_mantle/openai.gpt-oss-safeguard-20b", "slug": "bedrock_mantle-bedrock_mantle-openai-gpt-oss-safeguard-20b", "provider": "bedrock_mantle", "providerSlug": "bedrock_mantle", "name": "openai.gpt-oss-safeguard-20b", "displayName": "openai.gpt-oss-safeguard-20b", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 0.075, "outputUsdPer1MTokens": 0.3, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 0.075, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7 } }, "limits": { "contextWindow": 65536, "maxInputTokens": 131072, "maxOutputTokens": 65536, "maxTokens": 65536, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "response_schema": true, "tool_choice": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock_mantle/openai.gpt-oss-safeguard-20b", "syncedAt": "2026-05-28" }, "rawLitellm": { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "benchmarks": { "local_aime2025notools_accuracy_gptoss120b_officialmodelcard_255": { "label": "AIME 2025 (no tools)", "category": "math", "score": 92.5, "scoreText": "92.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_aime2025notools_accuracy_gptoss20b_officialmodelcard_256": { "label": "AIME 2025 (no tools)", "category": "math", "score": 91.7, "scoreText": "91.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss120b_officialmodelcard_257": { "label": "GPQA Diamond", "category": "science", "score": 80.1, "scoreText": "80.1%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_gpqadiamondnotools_accuracy_gptoss20b_officialmodelcard_258": { "label": "GPQA Diamond", "category": "science", "score": 71.5, "scoreText": "71.5%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss120b_officialmodelcard_259": { "label": "MMLU", "category": "general_knowledge", "score": 90, "scoreText": "90.0%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_mmlu_accuracy_gptoss20b_officialmodelcard_260": { "label": "MMLU", "category": "general_knowledge", "score": 85.3, "scoreText": "85.3%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss120b_officialmodelcard_261": { "label": "SWE-bench Verified", "category": "coding", "score": 62.4, "scoreText": "62.4%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_swebenchverified_accuracy_gptoss20b_officialmodelcard_262": { "label": "SWE-bench Verified", "category": "coding", "score": 60.7, "scoreText": "60.7%", "metric": "Accuracy (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss120b_officialmodelcard_263": { "label": "Codeforces (with tools)", "category": "coding", "score": 2622, "scoreText": "2622", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_codeforceswithtools_elo_gptoss20b_officialmodelcard_264": { "label": "Codeforces (with tools)", "category": "coding", "score": 2516, "scoreText": "2516", "metric": "Elo", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Table 3, high reasoning column." }, "local_healthbench_score_gptoss120b_officialmodelcard_265": { "label": "HealthBench", "category": "other", "score": 57.6, "scoreText": "57.6%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_healthbench_score_gptoss20b_officialmodelcard_266": { "label": "HealthBench", "category": "other", "score": 42.5, "scoreText": "42.5%", "metric": "Score (%)", "higherIsBetter": true, "source_url": "https://cdn.openai.com/pdf/419b6906-9da6-406c-a19d-1bb078ac7637/oai_gpt-oss_model_card.pdf", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "gpt-oss-20b", "modelDeveloper": "OpenAI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Health performance table; high reasoning column." }, "local_artificialanalysisintelligenceindex_score_openaigptoss20bfree_benchmarkleaderboard_285": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 24.5, "scoreText": "24.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; do not generalize this to all providers." }, "local_artificialanalysiscodingindex_score_openaigptoss20bfree_benchmarkleaderboard_286": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 18.5, "scoreText": "18.5", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisagenticindex_score_openaigptoss20bfree_benchmarkleaderboard_287": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 27.6, "scoreText": "27.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_gpqadiamond_accuracy_openaigptoss20bfree_benchmarkleaderboard_288": { "label": "GPQA Diamond", "category": "reasoning", "score": 68.8, "scoreText": "68.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_hle_accuracy_openaigptoss20bfree_benchmarkleaderboard_289": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 9.8, "scoreText": "9.8%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_ifbench_accuracy_openaigptoss20bfree_benchmarkleaderboard_290": { "label": "IFBench", "category": "reasoning", "score": 65.1, "scoreText": "65.1%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_scicode_accuracy_openaigptoss20bfree_benchmarkleaderboard_291": { "label": "SciCode", "category": "coding", "score": 34.4, "scoreText": "34.4%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_terminalbenchhard_accuracy_openaigptoss20bfree_benchmarkleaderboard_292": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 10.6, "scoreText": "10.6%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/openai/gpt-oss-20b%3Afree/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-20b:free", "modelDeveloper": "OpenAI", "sourceType": "benchmark_leaderboard", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter benchmark page for the free route; model-level evidence only." }, "local_artificialanalysisintelligenceindex_score_openaigptoss120b_thirdpartyreport_293": { "label": "Artificial Analysis Intelligence Index", "category": "other", "score": 33.3, "scoreText": "33.3", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysiscodingindex_score_openaigptoss120b_thirdpartyreport_294": { "label": "Artificial Analysis Coding Index", "category": "coding", "score": 28.6, "scoreText": "28.6", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." }, "local_artificialanalysisagenticindex_score_openaigptoss120b_thirdpartyreport_295": { "label": "Artificial Analysis Agentic Index", "category": "agentic", "score": 37.9, "scoreText": "37.9", "metric": "score", "higherIsBetter": true, "source_url": "https://openrouter.ai/compare/openai/gpt-oss-120b", "checked_at": "2026-05-31", "baseModelFamily": "gpt-oss", "exactModelOrSnapshot": "openai/gpt-oss-120b", "modelDeveloper": "OpenAI", "sourceType": "third_party_report", "providerRouteScope": "base_model_only", "confidence": "high", "note": "OpenRouter compare page; this is not a provider-route-specific benchmark." } } }, { "id": "volcengine/volcengine/doubao-seed-2-0-pro-260215", "slug": "volcengine-volcengine-doubao-seed-2-0-pro-260215", "provider": "volcengine", "providerSlug": "volcengine", "name": "doubao-seed-2-0-pro-260215", "displayName": "doubao-seed-2-0-pro-260215", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 256000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "volcengine/doubao-seed-2-0-pro-260215", "syncedAt": "2026-05-28", "sourceUrl": "https://www.volcengine.com/docs/82379/1330310" }, "rawLitellm": { "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "source": "https://www.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 4.6e-7, "output_cost_per_token": 0.0000023, "range": [ 0, 32000 ] }, { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000035, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.000007, "range": [ 128000, 256000 ] } ] } }, { "id": "volcengine/volcengine/doubao-seed-2-0-lite-260215", "slug": "volcengine-volcengine-doubao-seed-2-0-lite-260215", "provider": "volcengine", "providerSlug": "volcengine", "name": "doubao-seed-2-0-lite-260215", "displayName": "doubao-seed-2-0-lite-260215", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 256000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "volcengine/doubao-seed-2-0-lite-260215", "syncedAt": "2026-05-28", "sourceUrl": "https://www.volcengine.com/docs/82379/1330310" }, "rawLitellm": { "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "source": "https://www.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 8.7e-8, "output_cost_per_token": 5.2e-7, "range": [ 0, 32000 ] }, { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 7.8e-7, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 2.6e-7, "output_cost_per_token": 0.0000016, "range": [ 128000, 256000 ] } ] } }, { "id": "volcengine/volcengine/doubao-seed-2-0-mini-260215", "slug": "volcengine-volcengine-doubao-seed-2-0-mini-260215", "provider": "volcengine", "providerSlug": "volcengine", "name": "doubao-seed-2-0-mini-260215", "displayName": "doubao-seed-2-0-mini-260215", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 256000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "volcengine/doubao-seed-2-0-mini-260215", "syncedAt": "2026-05-28", "sourceUrl": "https://www.volcengine.com/docs/82379/1330310" }, "rawLitellm": { "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "source": "https://www.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 2.9e-8, "output_cost_per_token": 2.9e-7, "range": [ 0, 32000 ] }, { "input_cost_per_token": 5.8e-8, "output_cost_per_token": 5.8e-7, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0.0000012, "range": [ 128000, 256000 ] } ] } }, { "id": "volcengine/volcengine/doubao-seed-2-0-code-preview-260215", "slug": "volcengine-volcengine-doubao-seed-2-0-code-preview-260215", "provider": "volcengine", "providerSlug": "volcengine", "name": "doubao-seed-2-0-code-preview-260215", "displayName": "doubao-seed-2-0-code-preview-260215", "mode": "chat", "pricing": { "inputUsdPer1MTokens": null, "outputUsdPer1MTokens": null, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": null, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": {} }, "limits": { "contextWindow": 128000, "maxInputTokens": 256000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": false, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "tool_choice": false, "vision": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "volcengine/doubao-seed-2-0-code-preview-260215", "syncedAt": "2026-05-28", "sourceUrl": "https://www.volcengine.com/docs/82379/1330310" }, "rawLitellm": { "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "source": "https://www.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 4.6e-7, "output_cost_per_token": 0.0000023, "range": [ 0, 32000 ] }, { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000035, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.000007, "range": [ 128000, 256000 ] } ] } }, { "id": "bedrock/bedrock/us-east-1/zai.glm-5", "slug": "bedrock-bedrock-us-east-1-zai-glm-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "zai.glm-5", "displayName": "zai.glm-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3.1999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-east-1/zai.glm-5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-zai-glm-5.html" ], "manual_model_modalities_note": "Bedrock exact regional alias from official docs." }, "benchmarks": { "hle_score_glm5_officialmodelcard_165": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 30.5, "scoreText": "30.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "gpqadiamond_score_glm5_officialmodelcard_166": { "label": "GPQA Diamond", "category": "reasoning", "score": 86, "scoreText": "86.0", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchverified_score_glm5_officialmodelcard_167": { "label": "SWE-bench Verified", "category": "coding", "score": 77.8, "scoreText": "77.8", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "bedrock/bedrock/us-west-2/zai.glm-5", "slug": "bedrock-bedrock-us-west-2-zai-glm-5", "provider": "Bedrock", "providerSlug": "bedrock", "name": "zai.glm-5", "displayName": "zai.glm-5", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1, "outputUsdPer1MTokens": 3.1999999999999997, "cachedInputUsdPer1MTokens": null, "cacheWriteUsdPer1MTokens": null, "cachedInputPriceStatus": "not_provided", "cacheWritePriceStatus": "not_provided", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032 } }, "limits": { "contextWindow": 128000, "maxInputTokens": 200000, "maxOutputTokens": 128000, "maxTokens": 128000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": false, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": false, "reasoning": true, "responseSchema": false, "systemMessages": true, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": false, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": false, "computerUse": false, "urlContext": false, "assistantPrefill": false, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "function_calling": true, "reasoning": true, "system_messages": true, "tool_choice": true } }, "modalities": { "supported": [ "text" ], "input": [ "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-west-2/zai.glm-5", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/bedrock/pricing/" }, "rawLitellm": { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-zai-glm-5.html" ], "manual_model_modalities_note": "Bedrock exact regional alias from official docs." }, "benchmarks": { "hle_score_glm5_officialmodelcard_165": { "label": "Humanity's Last Exam", "category": "reasoning", "score": 30.5, "scoreText": "30.5", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "gpqadiamond_score_glm5_officialmodelcard_166": { "label": "GPQA Diamond", "category": "reasoning", "score": 86, "scoreText": "86.0", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "swebenchverified_score_glm5_officialmodelcard_167": { "label": "SWE-bench Verified", "category": "coding", "score": 77.8, "scoreText": "77.8", "metric": "Score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/GLM-5", "checked_at": "2026-05-31", "baseModelFamily": "GLM-5", "exactModelOrSnapshot": "GLM-5", "modelDeveloper": "Zhipu AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model card; target is the first column of the comparison table." }, "local_mmlu_score_glm49b_officialmodelcard_200": { "label": "MMLU", "category": "general_knowledge", "score": 74.7, "scoreText": "74.7", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_ceval_score_glm49b_officialmodelcard_201": { "label": "C-Eval", "category": "general_knowledge", "score": 77.1, "scoreText": "77.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gpqa_score_glm49b_officialmodelcard_202": { "label": "GPQA", "category": "science", "score": 34.3, "scoreText": "34.3", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_gsm8k_score_glm49b_officialmodelcard_203": { "label": "GSM8K", "category": "reasoning", "score": 84, "scoreText": "84.0", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_math_score_glm49b_officialmodelcard_204": { "label": "MATH", "category": "reasoning", "score": 30.4, "scoreText": "30.4", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." }, "local_humaneval_score_glm49b_officialmodelcard_205": { "label": "HumanEval", "category": "coding", "score": 70.1, "scoreText": "70.1", "metric": "score", "higherIsBetter": true, "source_url": "https://huggingface.co/zai-org/glm-4-9b-hf", "checked_at": "2026-05-31", "baseModelFamily": "GLM", "exactModelOrSnapshot": "GLM-4-9B", "modelDeveloper": "Zhipu AI / Z.AI", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "From the GLM-4-9B HF model card table." } } }, { "id": "bedrock/bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", "slug": "bedrock-bedrock-us-gov-east-1-anthropic-claude-haiku-4-5-20251001-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": 0.12, "cacheWriteUsdPer1MTokens": 1.5, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.0000015, "cache_read_input_token_cost": 1.2e-7, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true, "pdf_input": true } }, "modalities": { "supported": [ "image", "text" ], "input": [ "image", "text" ], "output": [ "text" ] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" }, "rawLitellm": { "cache_creation_input_token_cost": 0.0000015, "cache_read_input_token_cost": 1.2e-7, "input_cost_per_token": 0.0000012, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_pdf_input": true, "manual_model_modalities_review_status": "reviewed_official_docs_exact_model", "manual_model_modalities_source_urls": [ "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-4-5.html" ], "manual_model_modalities_note": "Bedrock exact GovCloud alias from official docs." }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } }, { "id": "bedrock/bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0", "slug": "bedrock-bedrock-us-gov-west-1-anthropic-claude-haiku-4-5-20251001-v1-0", "provider": "Bedrock", "providerSlug": "bedrock", "name": "anthropic.claude-haiku-4-5-20251001-v1:0", "displayName": "anthropic.claude-haiku-4-5-20251001-v1:0", "mode": "chat", "pricing": { "inputUsdPer1MTokens": 1.2, "outputUsdPer1MTokens": 6, "cachedInputUsdPer1MTokens": 0.12, "cacheWriteUsdPer1MTokens": 1.5, "cachedInputPriceStatus": "positive_raw_price", "cacheWritePriceStatus": "positive_raw_price", "reasoningOutputUsdPer1MTokens": null, "audioInputUsdPer1MTokens": null, "audioOutputUsdPer1MTokens": null, "imageInputUsdPer1MUnits": null, "imageOutputUsdPer1MUnits": null, "imageUsdPerImage": null, "embeddingUsdPer1MTokens": 1.2, "searchUsdPer1KCalls": null, "fileSearchUsdPer1KCalls": null, "vectorStoreUsdPerGbPerDay": null, "batchInputUsdPer1MTokens": null, "batchOutputUsdPer1MTokens": null, "batchCachedInputUsdPer1MTokens": null, "priorityInputUsdPer1MTokens": null, "priorityOutputUsdPer1MTokens": null, "priorityCachedInputUsdPer1MTokens": null, "flexInputUsdPer1MTokens": null, "flexOutputUsdPer1MTokens": null, "flexCachedInputUsdPer1MTokens": null, "above128kInputUsdPer1MTokens": null, "above128kOutputUsdPer1MTokens": null, "above200kInputUsdPer1MTokens": null, "above200kOutputUsdPer1MTokens": null, "above200kCachedInputUsdPer1MTokens": null, "above272kInputUsdPer1MTokens": null, "above272kOutputUsdPer1MTokens": null, "above272kCachedInputUsdPer1MTokens": null, "perSecondInputUsd": null, "perSecondOutputUsd": null, "perCharacterInputUsd": null, "perCharacterOutputUsd": null, "perPixelInputUsd": null, "perPixelOutputUsd": null, "ocrUsdPerPage": null, "codeInterpreterUsdPerSession": null, "rawPricing": { "cache_creation_input_token_cost": 0.0000015, "cache_read_input_token_cost": 1.2e-7, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006 } }, "limits": { "contextWindow": 64000, "maxInputTokens": 200000, "maxOutputTokens": 64000, "maxTokens": 64000, "maxImagesPerPrompt": null, "maxAudioPerPrompt": null, "maxAudioLengthHours": null, "maxPdfSizeMb": null, "maxVideoLength": null, "maxVideosPerPrompt": null, "outputVectorSize": null, "rpm": null, "tpm": null, "maxQueryTokens": null, "maxDocumentChunksPerQuery": null, "maxTokensPerDocumentChunk": null }, "capabilities": { "vision": true, "functionCalling": true, "parallelFunctionCalling": false, "toolChoice": true, "promptCaching": true, "reasoning": true, "responseSchema": true, "systemMessages": false, "audioInput": false, "audioOutput": false, "webSearch": false, "pdfInput": true, "videoInput": false, "nativeStreaming": false, "nativeStructuredOutput": true, "computerUse": true, "urlContext": false, "assistantPrefill": true, "serviceTier": false, "outputConfig": false, "reasoningEfforts": { "none": false, "minimal": false, "max": false, "xhigh": false }, "raw": { "assistant_prefill": true, "computer_use": true, "function_calling": true, "prompt_caching": true, "reasoning": true, "response_schema": true, "tool_choice": true, "vision": true, "native_structured_output": true, "pdf_input": true } }, "modalities": { "supported": [], "input": [], "output": [] }, "endpoints": [], "lifecycle": { "deprecationDate": null }, "source": { "type": "litellm", "litellmKey": "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0", "syncedAt": "2026-05-28", "sourceUrl": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock" }, "rawLitellm": { "cache_creation_input_token_cost": 0.0000015, "cache_read_input_token_cost": 1.2e-7, "input_cost_per_token": 0.0000012, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000006, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_pdf_input": true }, "benchmarks": { "swebenchverified_score_claudehaiku45_officialmodelcard_50": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "score", "higherIsBetter": true, "source_url": "https://www.anthropic.com/claude/haiku", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4-5", "modelDeveloper": "Anthropic", "sourceType": "official_model_card", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official model page SWE-bench score." }, "swebenchverified_resolved_claude45haikuhighreasoning_benchmarkleaderboard_218": { "label": "SWE-bench Verified", "category": "coding", "score": 66.6, "scoreText": "66.60%", "metric": "% resolved", "higherIsBetter": true, "source_url": "https://www.swebench.com/verified.html", "checked_at": "2026-05-31", "baseModelFamily": "Claude 4.5 Haiku", "exactModelOrSnapshot": "Claude 4.5 Haiku (high reasoning)", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "high", "note": "Official SWE-bench Verified leaderboard row for the high-reasoning variant." }, "swebenchverified_accuracy_claudehaiku45_officiallaunchpost_271": { "label": "SWE-bench Verified", "category": "coding", "score": 73.3, "scoreText": "73.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://www.anthropic.com/news/claude-haiku-4-5", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "official_launch_post", "providerRouteScope": "base_model_only", "confidence": "high", "note": "Official launch post. Anthropic explicitly reports 73.3% on SWE-bench Verified." }, "gpqadiamond_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_272": { "label": "GPQA Diamond", "category": "reasoning", "score": 67.2, "scoreText": "67.2%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "terminalbenchhard_passrate_anthropicclaudehaiku45_benchmarkleaderboard_273": { "label": "Terminal-Bench Hard", "category": "agentic", "score": 27.3, "scoreText": "27.3%", "metric": "pass rate", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." }, "ifbench_accuracy_anthropicclaudehaiku45_benchmarkleaderboard_274": { "label": "IFBench", "category": "other", "score": 54.3, "scoreText": "54.3%", "metric": "accuracy", "higherIsBetter": true, "source_url": "https://openrouter.ai/anthropic/claude-haiku-4.5/benchmarks", "checked_at": "2026-05-31", "baseModelFamily": "Claude Haiku 4.5", "exactModelOrSnapshot": "anthropic/claude-haiku-4.5", "modelDeveloper": "Anthropic", "sourceType": "benchmark_leaderboard", "providerRouteScope": "provider_route_specific", "confidence": "medium", "note": "Route-specific OpenRouter benchmark page. Metrics sourced from Artificial Analysis." } } } ]